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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 225765
    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_10_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
    k
    0.57
    otype
    0.50
    sk
    0.49
    shrink
    0.49
    øy
    0.48
    arello
    0.47
    K
    0.47
    sage
    0.47
    olium
    0.46
    sy
    0.46
    POSITIVE LOGITS
     conferma
    0.57
     δεν
    0.57
     novamente
    0.56
     фонд
    0.56
     felicidad
    0.55
    
    0.55
     sadece
    0.55
    ларга
    0.55
     компания
    0.54
     branco
    0.54
    Activations Density 0.000%

    No Known Activations