© 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. 9431
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to scientific publications, web programming, and medical terminology

    oai_token-act-pair · gemini-2.0-flash

    API and documentation

    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
     MainAxisSize
    -0.98
    ^(@)
    -0.96
     Jefus
    -0.95
     houſe
    -0.94
    }>;
    -0.91
    ########.
    -0.89
     Majefty
    -0.88
    tvguidetime
    -0.87
     Chrift
    -0.85
     Reſ
    -0.85
    POSITIVE LOGITS
    '
    0.68
    .
    0.65
    <bos>
    0.65
    ’
    0.57
    ​
    0.57
    ,
    0.56
    �
    0.52
    //
    0.52
     (
    0.52
    </b>
    0.52
    Activations Density 2.376%

    No Known Activations