© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 54901
    Prev
    Next
    INDEX
    Explanations

    section headings like Introduction or Abstract

    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_30_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
    ե
    0.38
     nationality
    0.37
     ప్రారం
    0.36
     tempted
    0.36
     pik
    0.36
     बाथरूम
    0.35
     Ceres
    0.35
    重
    0.35
     violence
    0.35
     ና
    0.35
    POSITIVE LOGITS
     মাঠ
    0.41
    uliar
    0.39
    ulador
    0.37
    killer
    0.37
    mere
    0.37
    érant
    0.37
     cardiologist
    0.36
    Killer
    0.35
    ologists
    0.35
    discussed
    0.35
    Activations Density 0.001%

    No Known Activations