© 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. 10540
    Prev
    Next
    INDEX
    Explanations

    a specific format of references to external documents like court cases or laws

    oai_token-act-pair · gemini-2.0-flash

    Names

    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
     estekak
    -0.73
    
    -0.68
    titleMargin
    -0.60
    protoimpl
    -0.59
    DataPropertyName
    -0.59
     חיצוניים
    -0.59
    hetamine
    -0.57
    μως
    -0.57
    tonode
    -0.54
     initComponents
    -0.54
    POSITIVE LOGITS
     médié
    0.52
     réinitial
    0.52
     réglable
    0.50
    始
    0.50
     rinnov
    0.50
    Reviewed
    0.49
    onto
    0.47
     idées
    0.47
     tulang
    0.46
    Gön
    0.46
    Activations Density 2.269%

    No Known Activations