© 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. 30328
    Prev
    Next
    INDEX
    Explanations

    Dogecoin

    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
    を表
    0.49
     Chemists
    0.49
    müş
    0.49
     Income
    0.48
     ملے
    0.46
     быстрее
    0.46
     Monetary
    0.46
     कर्ज
    0.45
     ט
    0.45
    home
    0.45
    POSITIVE LOGITS
     legitim
    0.55
    ност
    0.54
    这种
    0.52
    സീ
    0.51
    这
    0.48
    硅
    0.48
     denne
    0.47
     този
    0.46
    理由
    0.46
    𝗜
    0.46
    Activations Density 0.000%

    No Known Activations