© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11599
    Prev
    Next
    INDEX
    Explanations

    abbreviations and jargon related to biomedical research and cell biology, especially involving proteins and pathways.

    oai_token-act-pair · gemini-2.0-flash

    AK

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Signalez
    -0.68
    PreExecute
    -0.68
     PopupWindow
    -0.67
    ttino
    -0.66
     חיצוניים
    -0.66
     ModelExpression
    -0.65
    ronique
    -0.65
    FontOfSize
    -0.62
    gemeester
    -0.62
    setDuration
    -0.62
    POSITIVE LOGITS
    awaiter
    0.42
     muualla
    0.41
     Nell
    0.39
     balcón
    0.39
     pulso
    0.39
     oda
    0.39
     ges
    0.38
     pulito
    0.38
     Rear
    0.37
    getClassLoader
    0.37
    Activations Density 4.282%

    No Known Activations