© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 48113
    Prev
    Next
    INDEX
    Explanations

    probable cause

    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
    在
    0.82
    ك
    0.77
    נו
    0.76
    Мо
    0.75
    מו
    0.72
    ক
    0.72
    dır
    0.70
    ন
    0.70
    ي
    0.70
    In
    0.70
    POSITIVE LOGITS
    ys
    0.60
    í
    0.56
    .
    0.55
     railroad
    0.54
    ());
    0.53
     darkening
    0.51
     diagonals
    0.50
     hated
    0.49
    ਿਲ
    0.49
     animating
    0.49
    Activations Density 0.000%

    No Known Activations