© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 30182
    Prev
    Next
    INDEX
    Explanations

    larger, smaller, more, less

    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_31_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
    RP
    0.29
    最も
    0.27
     RP
    0.27
     among
    0.27
    等人
    0.26
     opér
    0.26
    nergie
    0.26
    MG
    0.25
     cite
    0.25
     $=\
    0.25
    POSITIVE LOGITS
     fussy
    0.29
    නයේ
    0.28
    oum
    0.27
     luxurious
    0.27
    prar
    0.26
     dealer
    0.26
    ದಲ್ಲಿ
    0.26
     dream
    0.25
     الأخرى
    0.25
     bigger
    0.25
    Activations Density 0.002%

    No Known Activations