© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 18786
    Prev
    Next
    INDEX
    Explanations

    '

    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_15_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
    ка
    0.61
    𝚘
    0.55
    [
    0.50
     本当
    0.50
    ）。
    0.50
    ＊
    0.48
     защита
    0.48
    接地
    0.48
    。”
    0.46
    𝚊
    0.46
    POSITIVE LOGITS
     více
    0.56
     yc
    0.51
     octagon
    0.50
     ogrod
    0.50
     égard
    0.49
     ots
    0.48
    uited
    0.48
     meer
    0.47
     lösen
    0.46
     kiosk
    0.46
    Activations Density 0.000%

    No Known Activations