© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 156730
    Prev
    Next
    INDEX
    Explanations

    universities or departments

    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_50_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
     board
    0.67
    board
    0.64
    Board
    0.55
     boards
    0.54
    板
    0.52
     OCD
    0.52
    BOARD
    0.51
    boards
    0.51
     बोर्ड
    0.50
     BOARD
    0.50
    POSITIVE LOGITS
    дового
    0.38
    ^{*}$-
    0.38
     subscriber
    0.37
     оли
    0.37
    nez
    0.37
     നാ
    0.36
     جلو
    0.36
    adine
    0.35
     ridurre
    0.35
     _$_
    0.35
    Activations Density 0.001%

    No Known Activations