© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 84881
    Prev
    Next
    INDEX
    Explanations

    листья, линейные, личное, лицензия

    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_0_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
     of
    1.71
    ي
    1.36
    د
    1.33
    \
    1.32
    ла
    1.25
     équipes
    1.22
    nél
    1.16
    iest
    1.13
    ਮ
    1.12
    i
    1.09
    POSITIVE LOGITS
    на
    1.41
     or
    1.19
    а
    1.10
    у
    1.10
    G
    1.09
    ᱐
    1.07
    ang
    1.02
    ០
    1.02
    できます
    1.01
     quarto
    1.01
    Activations Density 0.000%

    No Known Activations