© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 200491
    Prev
    Next
    INDEX
    Explanations

    в том виде, в том смысле

    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_6_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
    '
    1.10
    \
    0.86
     обита
    0.80
    ви
    0.79
    нг
    0.78
    uer
    0.78
    ivere
    0.78
    taine
    0.77
    вила
    0.77
    ufig
    0.76
    POSITIVE LOGITS
    o
    1.40
    as
    1.33
    er
    1.32
    ק
    1.32
    ل
    1.29
    ac
    1.28
    ام
    1.28
    ed
    1.27
    e
    1.27
    un
    1.26
    Activations Density 0.000%

    No Known Activations