© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 213253
    Prev
    Next
    INDEX
    Explanations

    baking ingredients

    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_50_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
     powder
    3.56
     Powder
    3.34
    粉
    3.25
    powder
    3.11
     powders
    3.08
    Pow
    3.03
     पाउडर
    3.02
     powdered
    2.84
     poudre
    2.67
     powdery
    2.58
    POSITIVE LOGITS
     ಕಲ
    0.37
    bookmarks
    0.36
    TaskId
    0.35
    TAG
    0.35
    蝿
    0.35
     vess
    0.34
    pipeline
    0.34
     Kiel
    0.34
    tags
    0.34
    鳇
    0.34
    Activations Density 0.009%

    No Known Activations