© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 209660
    Prev
    Next
    INDEX
    Explanations

    A100 GPU

    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_5_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
     ruso
    1.16
     piccoli
    1.09
    UZ
    1.07
     perovsk
    1.07
     is
    1.05
     has
    1.05
     secreto
    1.05
     bonito
    1.03
    Л
    1.00
     homosexual
    0.99
    POSITIVE LOGITS
    '
    1.29
    el
    1.12
    ار
    1.05
    ంగా
    1.04
    op
    1.03
    ap
    1.02
    il
    1.00
    ان
    0.94
    ip
    0.93
    en
    0.93
    Activations Density 0.000%

    No Known Activations