© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 32118
    Prev
    Next
    INDEX
    Explanations

    plotly.express (px)

    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_40_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
     draw
    0.52
    Draw
    0.46
    draw
    0.46
     draws
    0.46
     drawn
    0.44
     Draw
    0.43
     뽑
    0.43
     drew
    0.42
     drawing
    0.42
     dibuj
    0.41
    POSITIVE LOGITS
     quiso
    0.40
     bigotry
    0.39
    猪
    0.39
    ಣಿ
    0.38
    лыгы
    0.38
    জাহ
    0.37
     বিনষ্ট
    0.37
    硚
    0.37
    唐
    0.37
    υχ
    0.37
    Activations Density 0.001%

    No Known Activations