© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 79040
    Prev
    Next
    INDEX
    Explanations

    UGA, pygame, Oprah

    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_0_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
    to
    1.84
    on
    1.75
    ul
    1.73
    리
    1.60
    in
    1.59
    ro
    1.58
    the
    1.56
    ra
    1.53
    as
    1.49
    p
    1.48
    POSITIVE LOGITS
    1.68
     for
    1.44
     It
    1.22
    、
    1.19
     For
    1.09
     a
    1.02
    使用
    1.02
    东西
    1.02
    ف
    0.98
    必要な
    0.98
    Activations Density 0.001%

    No Known Activations