© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 58528
    Prev
    Next
    INDEX
    Explanations

    Cyrillic fragments

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    步
    0.51
    數
    0.50
    이
    0.50
    大學
    0.48
    轉
    0.48
    미
    0.47
     미
    0.46
    廳
    0.46
    된
    0.45
     其他
    0.45
    POSITIVE LOGITS
     бен
    0.49
     мо
    0.46
     або
    0.45
     але
    0.44
     Ев
    0.42
     ви
    0.42
     ова
    0.41
     су
    0.41
     тан
    0.40
     аксе
    0.40
    Activations Density 0.000%

    No Known Activations