© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 138891
    Prev
    Next
    INDEX
    Explanations

    storage locations

    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_46_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
     tiled
    0.50
     Bald
    0.46
    煮
    0.44
     washing
    0.44
     knocking
    0.40
    ‖
    0.39
     ema
    0.39
     روب
    0.38
    বীন্দ্রনাথ
    0.38
     tagging
    0.37
    POSITIVE LOGITS
    foundation
    0.44
     फाउंडेशन
    0.41
    root
    0.40
     Foundation
    0.39
    milk
    0.39
    feather
    0.38
    缪
    0.38
    引领
    0.38
    smoke
    0.37
     विधायक
    0.37
    Activations Density 0.001%

    No Known Activations