© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14981
    Prev
    Next
    INDEX
    Explanations

    harm principle

    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_13_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     მხ
    0.55
    खाने
    0.55
    ρώ
    0.54
    aucune
    0.54
    ווה
    0.53
    7
    0.51
    0
    0.51
     roar
    0.50
    ك
    0.50
     flange
    0.49
    POSITIVE LOGITS
    读书
    0.49
    %\
    0.45
    的速度
    0.44
     Дон
    0.44
     |
    0.44
     törté
    0.44
     литературы
    0.42
    economics
    0.41
    籶
    0.41
    epine
    0.41
    Activations Density 0.024%

    No Known Activations