© 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. 210508
    Prev
    Next
    INDEX
    Explanations

    color descriptions ending in 'ish'

    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
    in
    1.24
    y
    1.06
    a
    0.93
    s
    0.90
    d
    0.87
    t
    0.86
    disease
    0.82
    i
    0.82
    ig
    0.82
    inins
    0.80
    POSITIVE LOGITS
    지가
    0.65
    ض
    0.63
     fern
    0.57
    에요
    0.54
     Beaux
    0.52
     ferns
    0.52
    戕
    0.52
     of
    0.51
    াপ
    0.51
     Beleza
    0.51
    Activations Density 0.000%

    No Known Activations