© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 215970
    Prev
    Next
    INDEX
    Explanations

    montane

    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_5_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
    1.20
    ?
    1.08
    .
    1.01
    ร
    1.00
     up
    0.97
     goofy
    0.95
    tas
    0.95
     you
    0.94
    。
    0.93
    टी
    0.92
    POSITIVE LOGITS
    ين
    1.70
    b
    1.66
    á
    1.63
    ع
    1.61
    c
    1.57
    지
    1.52
    un
    1.50
    า
    1.48
    g
    1.41
    де
    1.36
    Activations Density 0.001%

    No Known Activations