© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 170311
    Prev
    Next
    INDEX
    Explanations

    draw

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    冒险
    0.37
    +'
    0.36
    हून
    0.36
    ධා
    0.35
    ยิ่ง
    0.35
    ئیں
    0.35
    釁
    0.35
    vmin
    0.34
    暢
    0.34
    Với
    0.34
    POSITIVE LOGITS
     draw
    1.02
    draw
    0.92
     Draw
    0.92
    Draw
    0.90
     drawing
    0.88
     drawings
    0.86
     DRAW
    0.86
     draws
    0.84
     Drawing
    0.84
    Drawing
    0.82
    Activations Density 0.000%

    No Known Activations