© 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. 1818
    Prev
    Next
    INDEX
    Explanations

    people with titles and/or associated with organizations

    oai_token-act-pair · gemini-2.0-flash

    technical keywords or specific formatting patterns

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

    people and their titles

    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
    yle
    -0.54
    ın
    -0.48
    }{*}{}
    -0.47
    യ
    -0.46
     aside
    -0.46
    Referencer
    -0.46
     hey
    -0.46
    YLE
    -0.44
    vair
    -0.43
    ;->
    -0.42
    POSITIVE LOGITS
    DockStyle
    0.94
    RectangleBorder
    0.81
     Anſ
    0.75
    帖最后由
    0.74
     cauſe
    0.74
    extAlignment
    0.74
     Мексичка
    0.73
     reaſon
    0.71
     ſtre
    0.71
     GoogleFonts
    0.69
    Activations Density 0.597%

    No Known Activations