© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7597
    Prev
    Next
    INDEX
    Explanations

    words closely related to the Github platform and git version control.

    oai_token-act-pair · gemini-2.0-flash

    git commits

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    matchCondition
    -0.68
    bParam
    -0.60
     للمعارف
    -0.60
    mybatisplus
    -0.56
    WithIOException
    -0.55
    doctype
    -0.54
     BorderRadius
    -0.54
    InjectAttribute
    -0.51
    клопе
    -0.50
    DllImport
    -0.50
    POSITIVE LOGITS
     commit
    1.23
     commits
    1.15
     Commit
    1.11
    commit
    1.03
    Commit
    1.00
     COMMIT
    0.98
     git
    0.97
     repository
    0.96
     committed
    0.94
     commitment
    0.93
    Activations Density 3.658%

    No Known Activations