© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 138158
    Prev
    Next
    INDEX
    Explanations

    liquid water

    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_12_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
    SINGLE
    0.54
     vibrate
    0.53
     tỏa
    0.53
    ার্টমেন্ট
    0.53
    푀
    0.53
     تھے
    0.52
    ACKNOWLEDGMENTS
    0.52
    μένες
    0.51
    дентификаторы
    0.51
    étaient
    0.51
    POSITIVE LOGITS
    c
    0.71
    os
    0.63
    b
    0.61
    inda
    0.60
    ive
    0.59
    li
    0.59
    o
    0.57
     b
    0.56
    nen
    0.56
    eln
    0.56
    Activations Density 0.017%

    No Known Activations