© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 121953
    Prev
    Next
    INDEX
    Explanations

    DaVinci Resolve

    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_3_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
    s
    0.83
    u
    0.75
    in
    0.68
    sset
    0.64
    bacteria
    0.64
    uah
    0.63
    ϻ
    0.62
    beyblade
    0.61
    시
    0.61
    cience
    0.61
    POSITIVE LOGITS
     voldoende
    0.67
    الي
    0.63
    ال
    0.63
     eind
    0.61
    ágina
    0.61
     Zeitpunkt
    0.61
    娌
    0.61
    ő
    0.59
     heeft
    0.58
     financi
    0.58
    Activations Density 0.000%

    No Known Activations