© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    4. 128944
    Prev
    Next
    INDEX
    Explanations

    canopy interception or canopies

    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
    Negative Logits
    harth
    1.03
     italiani
    0.99
    ндары
    0.99
    出
    0.99
    attro
    0.96
    ейчас
    0.96
    ara
    0.96
    jobNumber
    0.95
    cèle
    0.94
    textColour
    0.94
    POSITIVE LOGITS
     a
    1.40
    IT
    1.36
     with
    1.24
     of
    1.13
     jeopard
    1.10
     the
    1.09
    1
    1.08
     pile
    1.04
     on
    1.02
     from
    1.01
    Activations Density 0.000%

    No Known Activations