© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136852
    Prev
    Next
    INDEX
    Explanations

    James Bond films and characters

    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_12_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
     се
    0.59
     ш
    0.57
     salt
    0.54
     перво
    0.52
     क्रिकेट
    0.52
     cricket
    0.51
     et
    0.50
     свои
    0.50
     е
    0.49
    '
    0.49
    POSITIVE LOGITS
    在北京
    0.60
    在中
    0.55
     Aquí
    0.53
    حده
    0.52
     Much
    0.51
     Ab
    0.50
    staande
    0.50
     Вообще
    0.50
    řej
    0.49
    ماع
    0.49
    Activations Density 0.001%

    No Known Activations