© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 18775
    Prev
    Next
    INDEX
    Explanations

    historical figures

    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_15_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
    ور
    0.13
    Фу
    0.13
    Б
    0.13
    OL
    0.12
    и
    0.12
    Ֆ
    0.12
    인
    0.12
    لا
    0.12
    3
    0.12
    À
    0.12
    POSITIVE LOGITS
     adversely
    0.14
     disastrous
    0.13
     ook
    0.12
     witnessed
    0.12
     גם
    0.12
     ridiculed
    0.12
     costly
    0.12
     রা
    0.11
     unwarranted
    0.11
     whistling
    0.11
    Activations Density 0.305%

    No Known Activations