© 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. 109312
    Prev
    Next
    INDEX
    Explanations

    a taste of

    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
    ς
    1.04
    ')):
    1.02
    них
    1.00
    %)
    0.99
    </h2>
    0.99
    ਮ
    0.96
    ור
    0.95
    ्स
    0.95
     )
    0.94
    んで
    0.93
    POSITIVE LOGITS
    ir
    1.23
    ر
    1.21
    ée
    1.16
    jší
    1.11
    l
    1.11
    ل
    1.05
    ного
    1.03
    ’
    1.02
    r
    1.02
    ed
    1.01
    Activations Density 0.001%

    No Known Activations