© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 135169
    Prev
    Next
    INDEX
    Explanations

    fields ending in ology

    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_1_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    3
    1.17
    4
    1.08
    لي
    1.00
    م
    0.99
     حيث
    0.98
    м
    0.97
    مي
    0.95
    рга
    0.94
    "
    0.94
    8
    0.94
    POSITIVE LOGITS
    can
    1.44
    in
    1.41
    al
    1.30
    er
    1.18
     can
    1.18
    ၀
    1.17
    called
    1.16
    IN
    1.10
    ۰
    1.09
    inya
    1.09
    Activations Density 0.001%

    No Known Activations