© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 10354
    Prev
    Next
    INDEX
    Explanations

    charset followed by "="

    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_40_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
     টেব
    0.47
    JsonResponse
    0.45
     توا
    0.41
     sao
    0.40
     venezolano
    0.39
    razier
    0.39
    adjustable
    0.39
     universitario
    0.38
     सिफारिश
    0.38
    盘
    0.38
    POSITIVE LOGITS
    epine
    0.41
    -‘
    0.39
    phis
    0.38
    役割
    0.38
    द्ध
    0.38
    ocamp
    0.38
    -'
    0.37
     Carr
    0.37
    бия
    0.37
     vare
    0.37
    Activations Density 0.003%

    No Known Activations