© 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. 10764
    Prev
    Next
    INDEX
    Explanations

    concepts, proper nouns, and words about politics, history, youth, and military

    oai_token-act-pair · 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
    boh
    -0.42
    hock
    -0.40
     članak
    -0.38
     occupational
    -0.37
    Sa
    -0.37
     ho
    -0.37
    ComponentModel
    -0.37
    スポンサー
    -0.37
     sponsors
    -0.37
     sponsored
    -0.36
    POSITIVE LOGITS
    RegressionTest
    0.85
    ГЛА
    0.82
     Jefus
    0.82
    elemField
    0.77
     itſelf
    0.77
     isInitialized
    0.75
     Monfieur
    0.75
    UnusedPrivate
    0.74
    addCriterion
    0.73
    TagMode
    0.73
    Activations Density 12.383%

    No Known Activations