© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 5486
    Prev
    Next
    INDEX
    Explanations

    docker commands and python scripts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    上がり
    0.67
    oline
    0.65
    utes
    0.62
    дер
    0.62
    w
    0.60
    foam
    0.60
    war
    0.59
     ill
    0.59
     hatches
    0.58
    vi
    0.57
    POSITIVE LOGITS
    TNumber
    0.82
    <unused2157>
    0.80
     esclusivamente
    0.79
     devez
    0.78
     seroton
    0.77
    ">=</
    0.77
     ইংরাজ
    0.77
     tikai
    0.75
     estás
    0.75
    <unused14>
    0.75
    Activations Density 0.004%

    No Known Activations