© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 30492
    Prev
    Next
    INDEX
    Explanations

    function `inspect` arguments

    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_10_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    k
    1.12
    ні
    0.95
    f
    0.91
     Međ
    0.89
    5
    0.88
    h
    0.86
    hund
    0.86
     of
    0.84
    image
    0.84
    Bankr
    0.83
    POSITIVE LOGITS
    ות
    1.09
    ы
    1.06
    αν
    0.95
    у
    0.91
    ট
    0.91
    મ
    0.81
    ան
    0.80
    น
    0.80
    ور
    0.77
    ض
    0.76
    Activations Density 0.029%

    No Known Activations