© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 59392
    Prev
    Next
    INDEX
    Explanations

    power window up feature

    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
     ventilation
    0.14
     ਜਾਂ
    0.13
     الفرق
    0.13
    큘
    0.13
     præ
    0.13
     ventil
    0.13
     проведение
    0.13
    牖
    0.13
    guh
    0.13
     apod
    0.12
    POSITIVE LOGITS
    Bitcoin
    0.16
    比特币
    0.15
    Архі
    0.13
    Perfil
    0.13
    Бар
    0.13
    Та
    0.13
    Ча
    0.13
    Coffee
    0.13
     sexy
    0.12
    اك
    0.12
    Activations Density 0.001%

    No Known Activations