© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 41170
    Prev
    Next
    INDEX
    Explanations

    insulting others

    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_11_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
     you
    0.68
     I
    0.67
    ্ডিং
    0.63
    I
    0.59
     You
    0.59
    \
    0.59
     with
    0.57
    In
    0.57
    Be
    0.57
     In
    0.56
    POSITIVE LOGITS
     оплаты
    0.63
    ता
    0.62
    원에서
    0.59
     мощности
    0.58
    р
    0.58
    мости
    0.56
     очки
    0.56
    ية
    0.55
    et
    0.55
    вар
    0.55
    Activations Density 0.002%

    No Known Activations