© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 64340
    Prev
    Next
    INDEX
    Explanations

    mucus

    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_46_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
     Bodies
    0.43
    =============
    0.40
    Drawable
    0.39
     კომპ
    0.38
     rootView
    0.38
    োধন
    0.37
     Corporal
    0.37
    сама
    0.37
    ඔ
    0.36
     tutt
    0.36
    POSITIVE LOGITS
     muk
    1.35
     muc
    1.32
    Muc
    1.32
     Muc
    1.29
    Muk
    1.23
     Muk
    1.19
    muc
    1.17
     mucous
    1.16
     mucus
    1.14
    muk
    1.09
    Activations Density 0.001%

    No Known Activations