© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9340
    Prev
    Next
    INDEX
    Explanations

    urine, kidneys, toxins

    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_13_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
    {
    0.52
    amant
    0.51
    am
    0.48
    com
    0.46
     t
    0.46
     worldwide
    0.45
    volt
    0.45
    om
    0.44
     overw
    0.44
    worldwide
    0.43
    POSITIVE LOGITS
    鲈
    0.57
    רי
    0.48
    ภา
    0.48
     Curious
    0.47
     کوچ
    0.47
    茯
    0.46
     इंद्र
    0.45
     Farn
    0.45
     Fin
    0.44
    स्फ
    0.44
    Activations Density 0.044%

    No Known Activations