© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9584
    Prev
    Next
    INDEX
    Explanations

    clauses or short sentences that involve "doing" and comparisons or judgements

    oai_token-act-pair · gemini-2.0-flash

    do, much, else

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     Audiodateien
    -0.74
     estimés
    -0.68
     jsPsych
    -0.68
    例文帳に追加
    -0.67
     שוליים
    -0.65
    __(/*!
    -0.65
     Nir
    -0.63
    (!__
    -0.63
     <",
    -0.62
     ويكيميديا
    -0.62
    POSITIVE LOGITS
    .
    0.49
     far
    0.44
     stesso
    0.41
    гона
    0.41
     personal
    0.40
     self
    0.40
     same
    0.40
     Shapiro
    0.39
     sao
    0.39
     do
    0.39
    Activations Density 1.022%

    No Known Activations