© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 242026
    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_40_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
     शाहिद
    0.41
     кле
    0.39
    漾
    0.39
    叼
    0.39
     biochemical
    0.38
     transactional
    0.38
    Transactional
    0.38
     Sex
    0.37
     serotonin
    0.37
    тиву
    0.37
    POSITIVE LOGITS
     ugly
    1.63
     Ugly
    1.42
    ugly
    1.41
     ugl
    1.39
    丑
    1.32
    醜
    1.28
     unsightly
    1.03
     unattractive
    1.00
     hideous
    0.96
     ug
    0.76
    Activations Density 0.057%

    No Known Activations