© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36447
    Prev
    Next
    INDEX
    Explanations

    obi-wan kenobi

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_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
    e
    0.64
    ้
    0.62
     the
    0.62
    க்கொண்டு
    0.61
    S
    0.59
     a
    0.58
     analy
    0.57
    i
    0.56
    ,}
    0.55
    एस
    0.55
    POSITIVE LOGITS
    in
    0.75
    ль
    0.75
    ml
    0.68
    ла
    0.66
    д
    0.66
    to
    0.63
    ین
    0.62
    ﻟ
    0.61
    мм
    0.61
    ministrazione
    0.60
    Activations Density 0.000%

    No Known Activations