© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 58236
    Prev
    Next
    INDEX
    Explanations

    Standard

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
     operation
    0.41
     opérations
    0.40
     sheltering
    0.39
     ops
    0.39
     Ops
    0.39
     &/
    0.38
    陥
    0.38
    操作
    0.37
     amenity
    0.37
     প্রবন্ধ
    0.36
    POSITIVE LOGITS
    Operating
    1.07
     Operating
    1.02
    operating
    0.93
     operating
    0.87
    操作系统
    0.57
    for
    0.54
     অপারেটিং
    0.54
     ऑपरेटिंग
    0.52
     for
    0.48
    árm
    0.44
    Activations Density 0.001%

    No Known Activations