© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1516
    Prev
    Next
    INDEX
    Explanations

    statistical analyses reporting hazard ratios, confidence intervals, and/or odds ratios

    oai_token-act-pair · gemini-2.0-flash

    hazard and odds ratio

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    usti
    -0.43
    หน
    -0.41
    Node
    -0.38
    rome
    -0.38
    jene
    -0.36
    dep
    -0.36
    hof
    -0.36
    ouden
    -0.35
    low
    -0.35
    ėmis
    -0.35
    POSITIVE LOGITS
     MainAxisSize
    0.87
    IntoConstraints
    0.80
    Бахар
    0.80
    SharedDtor
    0.78
    FXMLLoader
    0.78
    RenderAtEndOf
    0.77
     Paglinawan
    0.77
     endwhile
    0.77
    __':
    0.75
    brews
    0.73
    Activations Density 2.485%

    No Known Activations