© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 143664
    Prev
    Next
    INDEX
    Explanations

    During

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    芗
    0.42
    KeyValuePair
    0.40
    铄
    0.40
    piperidin
    0.39
     Firma
    0.39
     Nix
    0.38
    Harry
    0.38
     sun
    0.37
     অপসারণ
    0.37
    Sun
    0.37
    POSITIVE LOGITS
     TOTAL
    0.57
    総
    0.55
    Total
    0.55
     Total
    0.55
     total
    0.52
     टोटल
    0.51
    total
    0.50
     총
    0.50
     getTotal
    0.49
    Tổng
    0.48
    Activations Density 0.003%

    No Known Activations