© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136315
    Prev
    Next
    INDEX
    Explanations

    accounting system parameters

    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_12_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
    ياب
    0.20
    棸
    0.18
     نوع
    0.18
     повіт
    0.18
    uks
    0.17
    邑
    0.17
    iams
    0.17
    bff
    0.17
     высоте
    0.17
    ပေး
    0.16
    POSITIVE LOGITS
     Rohingya
    0.20
     Rohing
    0.19
     rescind
    0.18
    κης
    0.18
    讫
    0.18
    ری
    0.17
    ગુ
    0.17
     guarant
    0.17
     quibusdam
    0.17
     Savaşı
    0.17
    Activations Density 0.003%

    No Known Activations