© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 86434
    Prev
    Next
    INDEX
    Explanations

    co-working space

    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
    ದ
    0.90
    ما
    0.75
    in
    0.74
    ма
    0.74
    को
    0.73
    ovati
    0.72
    ス
    0.70
    д
    0.68
    েরও
    0.68
    ‌های
    0.68
    POSITIVE LOGITS
    that
    0.66
    w
    0.65
     Yeh
    0.64
    ;
    0.64
    for
    0.63
    n
    0.63
    fie
    0.62
    foy
    0.61
    #:
    0.60
     Leonid
    0.60
    Activations Density 0.000%

    No Known Activations