© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14516
    Prev
    Next
    INDEX
    Explanations

    New-Object System

    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_13_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
    ני
    0.56
    ان
    0.54
    рил
    0.53
    at
    0.52
    人
    0.52
    тся
    0.51
    ре
    0.50
    يريا
    0.48
    ص
    0.48
    ці
    0.48
    POSITIVE LOGITS
     आंकड़ों
    0.63
     Chaucer
    0.56
     미국의
    0.55
     प्रतीत
    0.55
     χρησιμοποι
    0.53
     социа
    0.53
     използва
    0.53
     Amerikan
    0.53
     amerikan
    0.52
     dejamos
    0.52
    Activations Density 0.002%

    No Known Activations