© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14955
    Prev
    Next
    INDEX
    Explanations

    noble titles and people

    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
     গবেষণ
    0.56
     профессор
    0.56
     исследования
    0.55
    給大家
    0.54
     магистра
    0.54
     Ꭰ
    0.53
    inguém
    0.52
     документа
    0.52
     \{\
    0.52
     उद्देश
    0.52
    POSITIVE LOGITS
     pc
    0.50
    pc
    0.50
    Landscape
    0.49
    Zap
    0.49
    oppos
    0.48
     manager
    0.47
    PC
    0.47
    ješ
    0.47
    服
    0.47
    purch
    0.47
    Activations Density 0.030%

    No Known Activations