© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 39444
    Prev
    Next
    INDEX
    Explanations

    action / activity

    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_11_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
    е
    0.77
    Б
    0.66
    К
    0.66
    Ма
    0.64
    Ре
    0.63
    Х
    0.62
    Би
    0.61
    i
    0.61
    ी
    0.60
    ي
    0.59
    POSITIVE LOGITS
     orgánica
    0.53
    মাদের
    0.52
    徸
    0.50
     resonate
    0.50
    助手
    0.49
     diseñ
    0.48
    觀察
    0.48
    ्यू
    0.46
    ulière
    0.46
    յան
    0.46
    Activations Density 0.001%

    No Known Activations