© 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. 126857
    Prev
    Next
    INDEX
    Explanations

    foosball table, Fauxton, Foundation

    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
    تي
    0.89
    (
    0.78
    ر
    0.75
    ských
    0.74
    人士
    0.72
    لية
    0.71
    ري
    0.69
    لر
    0.69
    يك
    0.67
    됐
    0.66
    POSITIVE LOGITS
    a
    0.88
    AR
    0.85
    d
    0.76
     {
    0.75
    aa
    0.73
     \
    0.73
     ה
    0.71
    ה
    0.71
    iy
    0.70
    UNT
    0.70
    Activations Density 0.003%

    No Known Activations