© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 58443
    Prev
    Next
    INDEX
    Explanations

    degrees, radian, cos, image, times

    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_2_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
     have
    0.93
     has
    0.89
     =
    0.84
    ាតុ
    0.83
     {
    0.81
     $\
    0.79
    ية
    0.79
     or
    0.78
     is
    0.78
    ias
    0.77
    POSITIVE LOGITS
    는
    1.33
    س
    1.26
    ۔
    1.15
    y
    1.09
    ओं
    1.03
    ן
    1.03
    ție
    1.02
    是
    1.02
    를
    1.00
     rozwiąz
    0.93
    Activations Density 0.078%

    No Known Activations