© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 174768
    Prev
    Next
    INDEX
    Explanations

    development

    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_24_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
    Prop
    0.39
    浏览
    0.39
     firmware
    0.37
     출시
    0.37
     απα
    0.37
    陪伴
    0.37
     माध्यमातून
    0.37
    fromRGBO
    0.37
     क्रमा
    0.36
    恪
    0.36
    POSITIVE LOGITS
    ks
    0.43
     relatively
    0.42
     relativamente
    0.40
    ksi
    0.40
    issons
    0.39
     Haiti
    0.39
    če
    0.38
     KS
    0.38
     Haitian
    0.38
     LH
    0.38
    Activations Density 0.002%

    No Known Activations