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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 15-GEMMASCOPE-2-TRANSCODER-262K
    4. 16547
    Prev
    Next
    INDEX
    Explanations

    area calculation or definition

    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_15_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
    ’
    0.56
    वण्यासाठी
    0.53
     c
    0.51
    '
    0.50
    gunaan
    0.49
    ver
    0.49
     ligaments
    0.48
     dislocations
    0.48
    ліся
    0.47
    t
    0.47
    POSITIVE LOGITS
     modos
    0.60
     ዓይነት
    0.57
    体验
    0.57
     면
    0.55
     опыт
    0.54
     мето
    0.53
     后
    0.53
     愛
    0.53
    URDAY
    0.53
    Ỳ
    0.53
    Activations Density 0.007%

    No Known Activations