© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 38113
    Prev
    Next
    INDEX
    Explanations

    Deng Xiaoping's Reform and Opening Up

    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_3_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
    ।
    0.69
     стра
    0.57
     scared
    0.57
    trecht
    0.57
     типов
    0.57
     або
    0.56
    ции
    0.55
    па
    0.55
    toires
    0.55
     в
    0.54
    POSITIVE LOGITS
    ع
    0.86
    ح
    0.84
    ic
    0.77
    ل
    0.74
    S
    0.71
     or
    0.71
    л
    0.71
    ik
    0.67
    ע
    0.66
    ash
    0.64
    Activations Density 0.000%

    No Known Activations