© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 162566
    Prev
    Next
    INDEX
    Explanations

    COPD

    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_2_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
    '
    1.81
    し
    1.60
    ب
    1.34
    ام
    1.31
    를
    1.16
    क
    1.09
    ມີ
    1.09
     aches
    1.09
    א
    1.09
    то
    1.08
    POSITIVE LOGITS
    ri
    1.09
    datos
    1.03
     modellen
    0.99
    d
    0.95
    AG
    0.95
     बढ़ते
    0.93
    all
    0.89
     modelli
    0.88
     dále
    0.88
     الدولية
    0.86
    Activations Density 0.001%

    No Known Activations