© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 60705
    Prev
    Next
    INDEX
    Explanations

    deferential language

    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
     and
    0.55
    ע
    0.48
    ीन
    0.48
    د
    0.47
    แ
    0.47
     at
    0.46
     diferencial
    0.45
    ד
    0.45
     daug
    0.45
    א
    0.45
    POSITIVE LOGITS
     फुटबॉल
    0.52
    gefühl
    0.50
     Melihat
    0.49
     heady
    0.49
    ibban
    0.48
    要因
    0.48
    choices
    0.47
    zeiten
    0.47
     Дей
    0.47
     हिस्सों
    0.46
    Activations Density 0.001%

    No Known Activations