© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 30839
    Prev
    Next
    INDEX
    Explanations

    within, out, obligation, correlation, weeks, about, algorithms, everything

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    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
    幷
    0.36
    ⚘
    0.36
     ။
    0.35
    etragen
    0.35
     нә
    0.35
    폿
    0.34
     userRoutes
    0.34
     واذا
    0.34
     ♦
    0.34
    *{
    0.33
    POSITIVE LOGITS
    icos
    0.37
    eler
    0.36
    aph
    0.35
     টেস্ট
    0.35
    ric
    0.35
    elp
    0.35
    mps
    0.34
    astrophe
    0.34
    ology
    0.33
    ouss
    0.33
    Activations Density 0.075%

    No Known Activations