© 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. 87163
    Prev
    Next
    INDEX
    Explanations

    out with

    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
    ia
    0.71
    s
    0.68
    어
    0.67
     duet
    0.66
    o
    0.66
     bezel
    0.64
     profundamente
    0.62
    e
    0.61
     tack
    0.61
    ไฟล์
    0.61
    POSITIVE LOGITS
    p
    1.02
    tr
    0.86
    c
    0.81
    paren
    0.73
    center
    0.71
    cı
    0.70
    millimeters
    0.69
    تها
    0.69
     இழ
    0.69
    tration
    0.68
    Activations Density 0.000%

    No Known Activations