© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 108637
    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_2_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
     DAO
    1.01
    在
    1.01
    ：
    0.99
    ও
    0.94
    un
    0.93
     CPU
    0.91
    ud
    0.90
    0.89
     SRAM
    0.88
     ORNL
    0.87
    POSITIVE LOGITS
    s
    1.03
    ς
    1.03
    \
    0.99
    는
    0.96
    ா
    0.95
    the
    0.95
     продуктов
    0.93
    욱
    0.87
    рт
    0.86
    ों
    0.86
    Activations Density 0.000%

    No Known Activations