© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 86517
    Prev
    Next
    INDEX
    Explanations

    GGML or Georgi Gerganov Machine Learning

    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_3_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
    ق
    0.79
    ס
    0.67
    cation
    0.60
    دو
    0.60
     मुआव
    0.60
    ان
    0.59
     abril
    0.57
    जा
    0.55
    ف
    0.55
     усі
    0.55
    POSITIVE LOGITS
    -
    0.66
    ри
    0.66
    '
    0.64
    ي
    0.63
    學院
    0.61
    的作用
    0.60
    ur
    0.59
    ে
    0.58
    ி
    0.57
    <0xA5>
    0.57
    Activations Density 0.003%

    No Known Activations