© 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. 11924
    Prev
    Next
    INDEX
    Explanations

    plant construction and operation

    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
    れの
    0.41
     टें
    0.40
     え
    0.39
     গাছের
    0.38
     Хан
    0.38
    子の
    0.38
     ক্র
    0.37
    리면
    0.37
    ットフォーム
    0.37
     壁
    0.37
    POSITIVE LOGITS
    '
    0.46
    ol
    0.42
    ب
    0.42
    azz
    0.39
    oly
    0.38
    s
    0.38
    ao
    0.38
    bis
    0.38
    istir
    0.38
    igger
    0.36
    Activations Density 0.016%

    No Known Activations