© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 93487
    Prev
    Next
    INDEX
    Explanations

    followings Anhänger

    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
     zu
    0.54
    PR
    0.52
    KI
    0.52
    EDI
    0.52
    eden
    0.50
    ’
    0.50
     giornata
    0.50
     /
    0.49
     for
    0.48
     doi
    0.48
    POSITIVE LOGITS
    특별시
    0.55
    人々
    0.54
     kucch
    0.52
    คุณ
    0.50
    ურთიერთ
    0.50
     መሳሪያ
    0.50
    払い
    0.49
    ետ
    0.49
    <unused1067>
    0.48
    人們
    0.48
    Activations Density 0.000%

    No Known Activations