© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12516
    Prev
    Next
    INDEX
    Explanations

    this neuron identifies named entities, especially people and organizations, and also clauses that include "it," "which," or a pronoun.

    oai_token-act-pair · gemini-2.0-flash

    legal and political actions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     approving
    -0.63
     closed
    -0.59
     approve
    -0.57
     rejecting
    -0.57
     denying
    -0.57
     refusal
    -0.56
    Denied
    -0.55
    Closed
    -0.54
     refusing
    -0.54
     Den
    -0.54
    POSITIVE LOGITS
    RenderAtEndOf
    0.82
    DockStyle
    0.71
    Gambas
    0.68
    InitVars
    0.60
    UnitTesting
    0.60
    titleMargin
    0.56
    GeneratedCode
    0.55
     المعيارى
    0.55
     CWE
    0.52
    alyptus
    0.51
    Activations Density 7.054%

    No Known Activations