© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 29898
    Prev
    Next
    INDEX
    Explanations

    a followed by descriptive words

    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_7_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
    c
    0.97
    m
    0.78
    l
    0.74
    '
    0.68
    v
    0.62
    z
    0.62
    b
    0.61
    w
    0.61
    k
    0.61
    is
    0.59
    POSITIVE LOGITS
     peonies
    0.44
    лога
    0.43
     scaffolds
    0.43
     agua
    0.42
     perros
    0.42
     utensils
    0.42
    вка
    0.41
     dumplings
    0.41
     Оксана
    0.41
     Олег
    0.41
    Activations Density 0.012%

    No Known Activations