© 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. 127039
    Prev
    Next
    INDEX
    Explanations

    %APPDATA% or %LOCALAPPDATA%

    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
    t
    1.01
    大
    0.72
    in
    0.63
    tan
    0.60
    ne
    0.59
    tion
    0.59
    tgt
    0.58
    vention
    0.57
    ए
    0.57
    sol
    0.57
    POSITIVE LOGITS
    ↵
    0.67
     веществ
    0.65
    痪
    0.63
     peux
    0.63
    ５
    0.60
    ႉ
    0.59
    を楽し
    0.57
    不开
    0.56
     as
    0.55
     ставкалары
    0.55
    Activations Density 0.000%

    No Known Activations