© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 50335
    Prev
    Next
    INDEX
    Explanations

    Biel, Biela, Bielefeld, Sousa, wick, scrupulously

    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_10_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
    ы
    0.86
    은
    0.73
    ের
    0.72
    ка
    0.71
    他
    0.64
    ер
    0.63
    ா
    0.60
    ą
    0.60
    TypeDef
    0.58
    ظيم
    0.58
    POSITIVE LOGITS
    ik
    0.85
     this
    0.81
    ний
    0.76
    Buenos
    0.72
    ش
    0.70
    них
    0.66
    ोसी
    0.64
    ő
    0.64
     in
    0.64
     it
    0.64
    Activations Density 0.000%

    No Known Activations