© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 31316
    Prev
    Next
    INDEX
    Explanations

    a way of explaining

    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_7_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
    t
    0.64
    ب
    0.56
    지
    0.56
     covariate
    0.52
    τερα
    0.50
    ಿರುವ
    0.49
    軧
    0.48
     সঞ্জীবনী
    0.48
    私募基金管理人
    0.47
    passe
    0.45
    POSITIVE LOGITS
    *
    0.63
    ,*
    0.57
     Че
    0.54
    UM
    0.53
     感
    0.52
     усі
    0.50
    :
    0.50
    IT
    0.49
    ®,
    0.49
    Χ
    0.49
    Activations Density 0.115%

    No Known Activations