© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 175510
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    ባቢ
    0.44
     Modelling
    0.40
     Loyalty
    0.40
     seeds
    0.37
    竰
    0.37
    prä
    0.36
     stamped
    0.36
     Lunch
    0.36
    zIndex
    0.36
     getValue
    0.36
    POSITIVE LOGITS
     khuôn
    0.40
    abbati
    0.39
     dab
    0.39
     gim
    0.38
    itans
    0.38
     Dab
    0.37
     مسی
    0.37
     tibial
    0.37
    梅
    0.37
    renamiento
    0.36
    Activations Density 0.000%

    No Known Activations