© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 148484
    Prev
    Next
    INDEX
    Explanations

    absence of something important

    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_23_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     لقب
    0.28
    iphone
    0.27
    isConnected
    0.26
     retina
    0.25
    Upcoming
    0.25
    okedex
    0.25
    Expenses
    0.25
    ㄑ
    0.25
    ޤ
    0.25
    Updates
    0.24
    POSITIVE LOGITS
     نگر
    0.27
     ми
    0.27
     Miłos
    0.27
     diversión
    0.26
     عاي
    0.26
     amma
    0.26
     SLOT
    0.25
    ächlich
    0.25
     такая
    0.25
     Ima
    0.25
    Activations Density 0.003%

    No Known Activations