© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 127797
    Prev
    Next
    INDEX
    Explanations

    original research

    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_3_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
    0
    0.80
    이어
    0.63
    이가
    0.59
    ０
    0.59
    тации
    0.57
    ০
    0.57
    BASE
    0.57
    远的
    0.55
    í
    0.55
    Tab
    0.55
    POSITIVE LOGITS
    م
    0.93
    on
    0.88
    м
    0.87
    s
    0.83
    एस
    0.79
    et
    0.70
    ↵
    0.68
    ς
    0.66
     словарь
    0.65
    。
    0.65
    Activations Density 0.003%

    No Known Activations