© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 232117
    Prev
    Next
    INDEX
    Explanations

    installation steps

    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_32_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
     фон
    0.40
     Gottes
    0.36
     اليه
    0.36
     लाइ
    0.35
     আন্ত
    0.35
    翊
    0.35
     ambient
    0.34
    correct
    0.34
    絆
    0.34
    xhtml
    0.34
    POSITIVE LOGITS
     compilers
    0.39
     github
    0.39
    osław
    0.38
    нинград
    0.38
     questionnaires
    0.37
     جائزے
    0.37
    编译
    0.36
    یط
    0.36
     cookbooks
    0.36
    র্প
    0.35
    Activations Density 0.002%

    No Known Activations