© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 11-GEMMASCOPE-2-TRANSCODER-262K
    4. 59459
    Prev
    Next
    INDEX
    Explanations

    multinational corporations

    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
    糍
    0.64
     at
    0.62
     приведен
    0.54
     prominently
    0.54
     жизнь
    0.53
     blemishes
    0.53
     इसी
    0.52
     गणित
    0.52
     উদ্ধ
    0.52
     чита
    0.51
    POSITIVE LOGITS
    м
    0.70
    م
    0.67
    am
    0.66
    un
    0.62
    ל
    0.61
    TypeOf
    0.58
    im
    0.56
    Tai
    0.55
    ac
    0.55
    ্ট
    0.53
    Activations Density 0.001%

    No Known Activations