© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4438
    Prev
    Next
    INDEX
    Explanations

    a combination of positive sentiment words near the word "report", as well as present participles

    oai_token-act-pair · gemini-2.0-flash

    reports and announcements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    thâu
    -0.83
     فريبيس
    -0.52
    ValueGeneration
    -0.50
    getWriter
    -0.42
    jsonPath
    -0.42
    wapV
    -0.41
    illoin
    -0.40
    argli
    -0.40
    benar
    -0.40
     Bioaccumulative
    -0.39
    POSITIVE LOGITS
    httphttps
    1.17
    <bos>
    0.80
    MigrationBuilder
    0.80
    出版年
    0.73
    MENAFN
    0.71
    CloseOperation
    0.69
    InvalidProtocol
    0.69
    ."</
    0.68
    脚注の使い方
    0.67
    |}{$
    0.67
    Activations Density 2.331%

    No Known Activations