© 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. 48279
    Prev
    Next
    INDEX
    Explanations

    price per person

    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
    Not in Any Lists

    No Comments

    Negative Logits
     schematically
    0.35
    厠
    0.35
     توا
    0.35
    QRSTUVWXYZ
    0.34
     дов
    0.33
     shoe
    0.33
    hear
    0.33
     Todos
    0.33
     Debian
    0.32
     Debye
    0.32
    POSITIVE LOGITS
    🦈
    0.36
     бюджет
    0.36
     ಪ್ರಮಾಣ
    0.36
    Interact
    0.34
    QUANT
    0.34
    社
    0.33
     सीधा
    0.33
    インパクト
    0.33
     Cámara
    0.33
    菟
    0.33
    Activations Density 0.003%

    No Known Activations