© 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. 59413
    Prev
    Next
    INDEX
    Explanations

    for the purpose of

    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
    i
    0.97
    et
    0.87
    us
    0.86
    o
    0.84
    ce
    0.75
    ul
    0.73
    ate
    0.71
    cles
    0.71
    ac
    0.70
    au
    0.70
    POSITIVE LOGITS
    の世界
    0.70
    ﺭ
    0.67
    ﺮ
    0.64
     Vũ
    0.64
    стите
    0.61
    ոն
    0.60
    ﻌ
    0.59
     에너지
    0.58
    能源
    0.57
     Música
    0.57
    Activations Density 0.000%

    No Known Activations