© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 26197
    Prev
    Next
    INDEX
    Explanations

    power generation facilities

    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_10_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
     kullanıcı
    0.64
     Ciebie
    0.61
     Câu
    0.59
     crainte
    0.58
    as
    0.57
     Até
    0.57
    ়
    0.57
    ON
    0.57
     traslad
    0.57
    y
    0.56
    POSITIVE LOGITS
    ن
    0.66
    美
    0.66
     feedwater
    0.62
    بول
    0.61
    н
    0.61
    pter
    0.58
    Тех
    0.58
    Ф
    0.57
    مد
    0.57
    に必要な
    0.57
    Activations Density 0.012%

    No Known Activations