© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4613
    Prev
    Next
    INDEX
    Explanations

    technical medical terminology and numbers used in describing studies.

    oai_token-act-pair · gemini-2.0-flash

    bowel movements and digestion

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     lenker
    -0.48
    pta
    -0.47
     graphiques
    -0.47
     ModelExpression
    -0.46
     QLabel
    -0.45
    Pont
    -0.44
     du
    -0.43
     cote
    -0.43
     durée
    -0.43
     veau
    -0.42
    POSITIVE LOGITS
    TintMode
    0.71
    extAlignment
    0.70
     gas
    0.67
    gebras
    0.63
    mybatisplus
    0.63
    __":
    0.60
     bezeichneter
    0.58
     ostavi
    0.57
     typelib
    0.57
    )"),
    0.56
    Activations Density 1.102%

    No Known Activations