© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1628
    Prev
    Next
    INDEX
    Explanations

    code documentation, specifically function definitions and docstrings marked by parentheses and quotation marks

    oai_token-act-pair · gemini-2.0-flash

    closing brackets and quotation marks

    np_token-act-pair-logits · gpt-4o-mini

    quotation marks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    fromnode
    -0.82
    setVerticalGroup
    -0.78
    writeField
    -0.75
    >*/
    -0.72
    RectangleBorder
    -0.71
    IUrlHelper
    -0.71
    LookAnd
    -0.69
    WriteTagHelper
    -0.69
    )];
    -0.68
     Winaray
    -0.67
    POSITIVE LOGITS
     médicale
    0.40
     néz
    0.39
     vaya
    0.39
    ftime
    0.38
     requerida
    0.38
     Celui
    0.37
    roek
    0.37
    上面的
    0.37
    stretchr
    0.37
    greif
    0.36
    Activations Density 0.261%

    No Known Activations