© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 36295
    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_31_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
     calorías
    0.41
    aksikan
    0.40
     Bud
    0.38
     myeloid
    0.38
     виртуа
    0.38
    炰
    0.38
     sağlam
    0.37
    物体
    0.37
     ಸಾ
    0.36
    शाली
    0.36
    POSITIVE LOGITS
     blemishes
    0.40
     imperfections
    0.39
     obstructions
    0.39
    卫
    0.39
     aesthetics
    0.37
     reparación
    0.37
     pests
    0.37
     réparation
    0.36
    ‍♀
    0.36
    伤
    0.36
    Activations Density 0.000%

    No Known Activations