© 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
    2. Gemma-3-27B-IT
    3. 11-GEMMASCOPE-2-TRANSCODER-262K
    4. 62696
    Prev
    Next
    INDEX
    Explanations

    specialarterialfactortime

    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_11_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
    ac
    0.73
    ak
    0.61
    ob
    0.60
    ascending
    0.59
    банк
    0.57
    բ
    0.57
    ба
    0.57
    බ්
    0.54
    balance
    0.53
    id
    0.52
    POSITIVE LOGITS
     of
    0.52
     Singing
    0.51
     laryng
    0.50
     Let
    0.49
     Wind
    0.49
     and
    0.49
     must
    0.48
     with
    0.48
     This
    0.47
     pear
    0.47
    Activations Density 0.000%

    No Known Activations