© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 23949
    Prev
    Next
    INDEX
    Explanations

    http or https links

    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_10_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
    n
    1.02
    g
    0.97
    c
    0.96
    p
    0.96
    an
    0.95
    t
    0.93
    f
    0.92
    u
    0.91
    l
    0.89
    h
    0.85
    POSITIVE LOGITS
     Artículo
    0.64
     Елена
    0.61
     cite
    0.60
     Система
    0.58
     Sử
    0.57
     использовать
    0.56
     deprecated
    0.56
    СФ
    0.56
     branchNode
    0.56
     is
    0.56
    Activations Density 0.018%

    No Known Activations