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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11748
    Prev
    Next
    INDEX
    Explanations

    semicolons in code and other formal languages

    oai_token-act-pair · gemini-2.0-flash

    semicolon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ,
    -3.38
    .
    -3.05
    ;
    -3.02
    :
    -2.69
    -
    -2.67
     (
    -2.59
     
    -2.48
    /
    -2.38
    <eos>
    -2.33
     in
    -2.25
    POSITIVE LOGITS
     myſelf
    5.47
     Efq
    5.25
     itſelf
    5.13
     Theſe
    4.97
     Monfieur
    4.94
     Jefus
    4.72
     Majefty
    4.59
     ſeveral
    4.56
     purpoſe
    4.56
     pleaſure
    4.53
    Activations Density 0.855%

    No Known Activations