© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6861
    Prev
    Next
    INDEX
    Explanations

    political leaders names

    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_39_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
     کمپیوٹر
    0.42
    计算机
    0.42
     컴퓨터
    0.41
    Bombay
    0.41
     کشمیر
    0.41
     Viscount
    0.41
    ᶤ
    0.40
     বঙ্গবন্ধু
    0.40
    ⇉
    0.40
     Mahatma
    0.38
    POSITIVE LOGITS
     Biden
    0.60
    Biden
    0.52
     Bolsonaro
    0.46
    Boris
    0.45
     Boris
    0.45
     Obrador
    0.44
     Xi
    0.44
    Xi
    0.44
     Zelensky
    0.43
     Volodymyr
    0.43
    Activations Density 0.088%

    No Known Activations