© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 34991
    Prev
    Next
    INDEX
    Explanations

    смотр(еть/ешь)

    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
    <0x0D>
    0.59
     korun
    0.51
    ولا
    0.49
    SPRING
    0.48
     szükséges
    0.46
    TA
    0.46
     Treats
    0.46
    Treat
    0.45
     to
    0.45
     リボン
    0.45
    POSITIVE LOGITS
     as
    0.55
    posable
    0.53
    ț
    0.53
    ți
    0.52
     quite
    0.52
     aunque
    0.52
    mé
    0.51
    ausible
    0.51
     apud
    0.50
     ganske
    0.50
    Activations Density 0.000%

    No Known Activations