© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 197906
    Prev
    Next
    INDEX
    Explanations

    amended, written, drafted, modified

    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_12_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
    and
    0.56
     c
    0.55
     Preservation
    0.53
    ctime
    0.52
    .
    0.51
    zim
    0.50
     Exclusion
    0.50
    partners
    0.50
    istico
    0.49
    _{\
    0.49
    POSITIVE LOGITS
     seductive
    0.65
     hypnotic
    0.56
     بير
    0.55
    РЕ
    0.55
    ნ
    0.54
    ЕН
    0.54
    ЕТ
    0.54
     КАК
    0.54
     մե
    0.53
     hip
    0.52
    Activations Density 0.000%

    No Known Activations