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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14781
    Prev
    Next
    INDEX
    Explanations

    punctuation, mostly dashes and quotation marks with other characters nearby

    oai_token-act-pair · gemini-2.0-flash

    em dash

    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
    out
    -0.78
     nakalista
    -0.77
     mapStateToProps
    -0.76
     isNameExpr
    -0.75
    most
    -0.73
     Thine
    -0.73
     doInBackground
    -0.72
     justly
    -0.72
    like
    -0.69
     muchacho
    -0.68
    POSITIVE LOGITS
     in
    0.60
     object
    0.60
     system
    0.59
     type
    0.58
     control
    0.57
     data
    0.57
     string
    0.57
     class
    0.56
     model
    0.56
     product
    0.56
    Activations Density 36.131%

    No Known Activations