© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 247428
    Prev
    Next
    INDEX
    Explanations

    mant followed by various endings

    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_40_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
     Craig
    0.38
    Craig
    0.38
     Kush
    0.37
    ปฏิ
    0.37
     supplic
    0.37
     새로
    0.37
     adver
    0.36
    تاج
    0.36
     sufferer
    0.36
    戴
    0.36
    POSITIVE LOGITS
     भागीदारों
    0.43
    iculture
    0.40
    ITC
    0.39
    ULTURE
    0.37
     filmed
    0.36
     ஒளி
    0.36
    質
    0.36
    CHAT
    0.35
     прийня
    0.35
    Owin
    0.35
    Activations Density 0.001%

    No Known Activations