© 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. 9424
    Prev
    Next
    INDEX
    Explanations

    dates, numbers, and years along with related words in specific contexts, such as elections, economics, software licenses, and food

    oai_token-act-pair · gemini-2.0-flash

    history and politics

    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
    Negative Logits
    <bos>
    -1.29
     дописавши
    -1.17
     betweenstory
    -1.16
     Италијани
    -1.15
    Autoritní
    -1.07
    PreferredItem
    -0.97
     виправивши
    -0.95
     незавершена
    -0.93
     ویکی‌پدی
    -0.93
    MigrationBuilder
    -0.93
    POSITIVE LOGITS
    ,
    0.50
    .
    0.48
     (
    0.47
     dom
    0.43
    :
    0.42
     po
    0.42
     M
    0.40
    ;
    0.39
     .
    0.39
    -
    0.39
    Activations Density 7.661%

    No Known Activations