© 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. 45009
    Prev
    Next
    INDEX
    Explanations

    LexisNexis

    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
    d
    0.72
    dies
    0.67
    l
    0.66
    mann
    0.63
    just
    0.61
    z
    0.61
    master
    0.60
    dem
    0.59
    mal
    0.59
    c
    0.59
    POSITIVE LOGITS
    ⴼ
    0.57
    地域の
    0.56
     hyperactivity
    0.56
    getLong
    0.54
     unsteady
    0.54
     proactive
    0.52
     ふ
    0.52
    混ぜ
    0.52
     landslides
    0.51
     divergent
    0.51
    Activations Density 0.000%

    No Known Activations