© 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. 29192
    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
    사는
    0.51
    ლებიც
    0.50
    갔
    0.50
    ایک
    0.48
     начал
    0.48
     وإن
    0.47
    が生
    0.47
    ൨
    0.47
    зд
    0.46
     laughed
    0.46
    POSITIVE LOGITS
    Shapes
    0.52
    s
    0.50
     Reihe
    0.48
     Ön
    0.46
    öss
    0.46
     estates
    0.43
     melhores
    0.43
     Earth
    0.43
    酮
    0.43
     Danny
    0.42
    Activations Density 0.000%

    No Known Activations