© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 33376
    Prev
    Next
    INDEX
    Explanations

    pack architecture

    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_3_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
    н
    0.68
    -
    0.66
    for
    0.61
    он
    0.60
     correr
    0.60
    ﺎ
    0.58
     strolling
    0.57
     mariage
    0.57
     vont
    0.57
    *
    0.57
    POSITIVE LOGITS
    in
    0.85
    ه
    0.82
    ע
    0.79
    ೆ
    0.70
    h
    0.67
     can
    0.67
    ا
    0.66
     was
    0.63
    uole
    0.63
    u
    0.61
    Activations Density 0.008%

    No Known Activations