© 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. 41385
    Prev
    Next
    INDEX
    Explanations

    kenji

    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
    i
    0.96
    ين
    0.88
    ي
    0.88
    →</
    0.71
    জ
    0.66
    די
    0.63
    يجي
    0.63
    mluv
    0.62
    ，
    0.62
    い
    0.60
    POSITIVE LOGITS
     softball
    0.66
     by
    0.63
     पहचा
    0.61
     glyph
    0.57
     frenzy
    0.57
     enumeration
    0.56
     on
    0.55
    อบ
    0.53
     тю
    0.53
     vehicles
    0.53
    Activations Density 0.001%

    No Known Activations