© 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
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 43765
    Prev
    Next
    INDEX
    Explanations

    code operations and imports

    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_13_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
    에서도
    0.50
    ी
    0.49
    ını
    0.49
    IA
    0.48
     ஆர்வ
    0.48
    ja
    0.48
    cta
    0.48
     cualquiera
    0.47
     ምክንያት
    0.47
    name
    0.46
    POSITIVE LOGITS
    kons
    0.46
    Ś
    0.46
    ล
    0.46
    skom
    0.46
     уси
    0.44
    पु
    0.44
    Vý
    0.43
     académ
    0.42
     svůj
    0.41
    êne
    0.41
    Activations Density 0.011%

    No Known Activations