© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 193837
    Prev
    Next
    INDEX
    Explanations

    LPI, RPA, LPA

    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_4_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
    ك
    0.69
    in
    0.68
    at
    0.59
    কে
    0.57
    ur
    0.53
    ת
    0.48
    ور
    0.47
    v
    0.46
    ক
    0.44
    1
    0.44
    POSITIVE LOGITS
    ↵
    0.47
     рассказа
    0.40
     политика
    0.40
     МО
    0.40
     αυτά
    0.38
     любо
    0.38
     знаем
    0.37
     начало
    0.37
     прой
    0.36
     saddhim
    0.36
    Activations Density 0.002%

    No Known Activations