© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1082
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially where a line ends with a semicolon and a return statement

    oai_token-act-pair · gemini-2.0-flash

    semicolon

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    saraba
    -0.56
    AutoScaleMode
    -0.47
     ***!
    -0.43
    getOut
    -0.42
     rever
    -0.42
    mergeFrom
    -0.42
    inander
    -0.42
    rawdę
    -0.41
     channel
    -0.41
    Filmografie
    -0.41
    POSITIVE LOGITS
     disambiguazione
    0.68
    DeleteBehavior
    0.64
    RenderAtEndOf
    0.61
     froide
    0.54
    énario
    0.54
    rrggbb
    0.54
    ूरत
    0.54
     TextAppearance
    0.53
    mybatisplus
    0.53
     يتيمه
    0.52
    Activations Density 2.173%

    No Known Activations