© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 78251
    Prev
    Next
    INDEX
    Explanations

    pelagic, peloponnesian, pelican, pelvic

    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
    Negative Logits
    ر
    1.84
    ב
    1.84
    ด
    1.74
    an
    1.73
    ه
    1.70
    л
    1.66
    د
    1.63
    ン
    1.62
    ز
    1.59
    ن
    1.57
    POSITIVE LOGITS
    5
    1.80
    9
    1.77
     by
    1.66
    6
    1.60
    ’
    1.56
     in
    1.48
     you
    1.37
     urin
    1.30
    0
    1.30
     a
    1.24
    Activations Density 0.000%

    No Known Activations