© 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. 51199
    Prev
    Next
    INDEX
    Explanations

    ri followed by specific letter sequences

    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
    ع
    0.99
    ка
    0.95
    ت
    0.91
    ك
    0.90
    рел
    0.90
    ма
    0.89
    נ
    0.89
    خ
    0.88
    大量
    0.86
    بيه
    0.86
    POSITIVE LOGITS
    s
    1.23
    ill
    1.10
    su
    1.05
    all
    1.00
    ation
    0.97
    li
    0.96
    ania
    0.93
    ara
    0.91
    ,
    0.87
    z
    0.87
    Activations Density 0.001%

    No Known Activations