© 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. 122311
    Prev
    Next
    INDEX
    Explanations

    putuo

    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
    ق
    0.90
    Imp
    0.87
    も
    0.78
     in
    0.77
    imped
    0.77
    imp
    0.75
    ك
    0.72
    of
    0.71
    两
    0.70
    ور
    0.68
    POSITIVE LOGITS
    нун
    0.79
    inę
    0.75
    inė
    0.74
    inį
    0.74
    ಃ
    0.71
    стве
    0.70
    ␊
    0.70
    leş
    0.70
    فی
    0.67
    лка
    0.67
    Activations Density 0.001%

    No Known Activations