© 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. 25632
    Prev
    Next
    INDEX
    Explanations

    about me:

    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
    ס
    1.00
    س
    0.93
    م
    0.92
    ל
    0.91
     can
    0.87
    스
    0.82
    Look
    0.82
    स
    0.81
    ล
    0.80
    Бу
    0.79
    POSITIVE LOGITS
    ningar
    0.61
    ning
    0.58
    繰
    0.56
     ακ
    0.55
    ্বন
    0.54
    司机
    0.53
     adquisición
    0.53
    ärt
    0.53
    ci
    0.52
     swelling
    0.52
    Activations Density 0.012%

    No Known Activations