© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9569
    Prev
    Next
    INDEX
    Explanations

    words/phrases from technical or scientific publications, especially those related to chemistry, biology, and medicine

    oai_token-act-pair · gemini-2.0-flash

    content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ↵
    -0.65
    ↵↵
    -0.64
     (
    -0.63
    ,
    -0.62
     
    -0.58
     in
    -0.57
    ;
    -0.54
    .
    -0.53
    '
    -0.52
    zení
    -0.50
    POSITIVE LOGITS
     Theſe
    1.21
     itſelf
    1.18
     Efq
    1.14
     Reſ
    1.14
     ſta
    1.13
     faſt
    1.13
     ſeveral
    1.10
     whoſe
    1.10
     myſelf
    1.09
     Majefty
    1.08
    Activations Density 5.146%

    No Known Activations