© 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. 45870
    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
    斯的
    0.57
    :')
    0.56
    斯
    0.56
    ی
    0.54
    '،
    0.52
    ”،
    0.51
    "،
    0.50
    یک
    0.49
    ۹
    0.48
    ین
    0.48
    POSITIVE LOGITS
     !=
    0.52
     requisition
    0.50
    Deviation
    0.48
     мероприятий
    0.45
     requis
    0.45
     $.
    0.44
    Management
    0.43
    への
    0.43
     ==
    0.42
     migr
    0.42
    Activations Density 0.000%

    No Known Activations