© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7416
    Prev
    Next
    INDEX
    Explanations

    class declarations

    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_39_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
     textColor
    0.37
     *$
    0.37
     ယ
    0.37
     lak
    0.37
    maj
    0.36
     revoked
    0.35
     Tires
    0.35
    াঙ্গা
    0.35
    𝑣
    0.35
     Inform
    0.35
    POSITIVE LOGITS
    LoggerFactory
    0.40
     Kent
    0.39
    なに
    0.37
    場の
    0.37
    각형
    0.37
    allergenic
    0.37
    បង្កើត
    0.36
     szyb
    0.36
    ünft
    0.36
     Ginkuhà
    0.36
    Activations Density 0.002%

    No Known Activations