© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 206537
    Prev
    Next
    INDEX
    Explanations

    deco(u)ctions, deco(u)page, couverte

    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_6_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
    n
    1.21
    at
    0.90
    lab
    0.88
    ↵↵
    0.86
    ering
    0.86
    ,
    0.86
    ink
    0.86
    that
    0.86
    ant
    0.85
    bak
    0.85
    POSITIVE LOGITS
     Și
    1.07
    يس
    1.05
    ی
    1.05
     കൂടുതൽ
    1.04
     Serrurier
    1.00
    ot
    0.99
    ON
    0.99
    О
    0.99
    Từ
    0.95
    Questo
    0.95
    Activations Density 0.000%

    No Known Activations