© 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. 32965
    Prev
    Next
    INDEX
    Explanations

    kidney stones and potassium

    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
    絡
    0.44
    嬌
    0.44
     Eddy
    0.42
     кры
    0.41
     CRT
    0.40
    IsMethod
    0.39
     Eu
    0.37
     Columbus
    0.37
     Crimson
    0.37
     cr
    0.37
    POSITIVE LOGITS
    Mono
    0.49
     citrate
    0.48
     mono
    0.46
    Cit
    0.43
     monoc
    0.42
    钽
    0.42
     cit
    0.42
     Ammonium
    0.41
     моно
    0.41
    mono
    0.40
    Activations Density 0.024%

    No Known Activations