© 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. 13032
    Prev
    Next
    INDEX
    Explanations

    references to figures, axes, and plots in scientific writing

    oai_token-act-pair · gemini-2.0-flash

    figure labels

    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
    ưới
    -0.50
     numerical
    -0.49
     stav
    -0.49
     plane
    -0.48
     fubject
    -0.48
    addPreferredGap
    -0.47
    tierten
    -0.46
    ̲
    -0.46
     Smy
    -0.46
     Numerical
    -0.46
    POSITIVE LOGITS
    expandindo
    0.71
     ExecuteAsync
    0.67
    KURZBESCHREIBUNG
    0.66
     Мексичка
    0.64
    Искәрмәләр
    0.62
     gynhyrchwyd
    0.61
    parsedMessage
    0.61
     referenties
    0.60
    exitRule
    0.59
    IndentedString
    0.58
    Activations Density 10.196%

    No Known Activations