© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 4281
    Prev
    Next
    INDEX
    Explanations

    Britannica biographies and science articles

    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_40_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
    경제
    0.38
     முதல்வர்
    0.37
     recto
    0.36
     terraz
    0.35
    Treasurer
    0.35
     विश्वसनीय
    0.35
    жными
    0.34
     προϊ
    0.34
    甕
    0.33
    횽
    0.33
    POSITIVE LOGITS
    ARRAY
    0.37
     solutions
    0.36
    arrays
    0.35
     solution
    0.35
    hum
    0.35
     Histories
    0.34
     Polygon
    0.34
    க்கமாக
    0.34
    yCoordinate
    0.34
     sci
    0.33
    Activations Density 0.000%

    No Known Activations