© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13059
    Prev
    Next
    INDEX
    Explanations

    words related to politics, law, and international relations.

    oai_token-act-pair · gemini-2.0-flash

    Policy

    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
    acat
    -0.48
    endere
    -0.45
    toni
    -0.43
    ABET
    -0.43
     pop
    -0.43
     kneel
    -0.42
    segno
    -0.41
     stile
    -0.40
     reine
    -0.40
     podí
    -0.40
    POSITIVE LOGITS
    addCriterion
    0.79
    findpost
    0.76
    AccessorTable
    0.72
    PRNewswire
    0.71
    Personensuche
    0.71
     snippetHide
    0.68
    providedIn
    0.67
    Tembelea
    0.66
     ModelExpression
    0.65
    yntaxException
    0.65
    Activations Density 0.961%

    No Known Activations