© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 251245
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    ‌های
    0.43
    pas
    0.43
    Pas
    0.42
     новая
    0.40
    Pins
    0.40
    噤
    0.39
     های
    0.38
    ('+
    0.38
    ẩ
    0.38
    ायचे
    0.37
    POSITIVE LOGITS
     læng
    0.54
     an
    0.53
     дов
    0.53
     Lange
    0.52
     longer
    0.51
     panjang
    0.51
     Longer
    0.49
     langer
    0.49
     길이가
    0.48
     läng
    0.47
    Activations Density 0.000%

    No Known Activations