Neuronscope

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/rudrendupaul-neuronscope

About

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list, install config and code. Checked Oct 26, 2026.

Tools

0 read · 2 write · 0 delete · 2 not yet classified

Secrets

None asked for

Install scripts

None found

Runs as

Python package

Tools (4)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

• activations

  Dump raw per-layer activation summary statistics (shape, mean, std, min/max, and the max-activating sequence position) for one prompt run through an open-weight TransformerLens-supported model, covering every layer's residual stream, MLP neuron activations, and attention pattern. Call this when trace's top-k ranking isn't enough detail and you need the raw scale/shape of a specific hook point before deciding what to inspect further or patch with the patch tool. Same model constraint as trace: only models HookedTransformer.from_pretrained supports. Read-only and deterministic for a given model …

• circuit

  Sketch a best-effort automated circuit for one prompt on an open-weight TransformerLens model: ranks candidate attention heads and MLP neurons by direct logit attribution, then measures each candidate's individual causal effect via single-component zero-ablation, so the result reflects components that actually move the prediction, not just ones correlated with it. Call this when trace's correlational ranking isn't enough and you want a causal pass across multiple candidates without manually calling patch on each one. This is NOT full path-patching with clean/corrupted prompt pairs and does not…

• patch

  Zero-ablate one component (a single transformer block's layer plus a component type such as an attention output or MLP output) in an open-weight TransformerLens model's forward pass, and report how the predicted token and its logit changed relative to the unablated baseline. This is a minimal causal intervention: use it to test whether a component trace or circuit flagged as correlated with a prediction is actually causally responsible for it. Call it after trace or circuit has surfaced a candidate layer/component; it does not search for candidates itself. Read-only in the sense that it writes…

• trace

  Run a forward pass of a small-to-medium open-weight language model (via TransformerLens) on one prompt, and report which attention heads and MLP neurons were most responsible for its predicted next token: heads ranked by direct logit attribution, neurons ranked by activation magnitude at the final prompt position. Call this to answer 'why did the model predict X' for a specific prompt. It only works on models TransformerLens's HookedTransformer.from_pretrained supports (GPT-2, Pythia, Llama, Gemma, Qwen, and similar open-weight checkpoints), not closed-source APIs like OpenAI or Anthropic mode…

Signals

Stars

1

Forks

0

Open issues

0

Weekly downloads

45

Last commit

Sep 25, 2026 (1 month ago)

Last release

Sep 25, 2026 (1 month ago)

Last package publish

Sep 25, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name

io.github.RudrenduPaul/neuronscope

Version

0.1.5

Auth

No auth

Packages

pypi neuronscope-cli

License

MIT

Repository

github.com/RudrenduPaul/NeuronScope

First seen

Oct 24, 2026

Last checked

Oct 24, 2026

Source

Official MCP Registrygithub-graphql