© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 201807
    Prev
    Next
    INDEX
    Explanations

    urine and excreta

    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_37_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
    chair
    0.44
     Chair
    0.43
    chairs
    0.43
     chair
    0.42
    责
    0.39
    椅子
    0.38
     Chairs
    0.38
     chairs
    0.37
    Chair
    0.37
     हीट
    0.37
    POSITIVE LOGITS
     urine
    0.50
    urine
    0.46
     моче
    0.46
    uria
    0.45
     Urine
    0.45
    尿
    0.45
     urinal
    0.44
     urin
    0.43
     urinary
    0.42
     urination
    0.40
    Activations Density 0.002%

    No Known Activations