© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 3774
    Prev
    Next
    INDEX
    Explanations

    words related to sports scores, seasons, and game play

    oai_token-act-pair · gemini-2.0-flash

    winning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    <bos>
    -0.77
    ↵
    -0.58
    [
    -0.53
     initComponents
    -0.51
    '
    -0.50
     
    -0.49
    ,
    -0.48
     eliminated
    -0.48
    RESUMO
    -0.47
    허
    -0.47
    POSITIVE LOGITS
     Efq
    0.91
     myſelf
    0.89
     Monfieur
    0.85
     Theſe
    0.84
     purpoſe
    0.83
     pleaſure
    0.82
     beſt
    0.80
     Majefty
    0.79
     becauſe
    0.78
    MigrationBuilder
    0.76
    Activations Density 1.816%

    No Known Activations