© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 235325
    Prev
    Next
    INDEX
    Explanations

    ballet and ballerina

    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_32_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
    רת
    0.37
    chore
    0.37
    Bloc
    0.37
    უკ
    0.37
     blocs
    0.36
    ೋಪ
    0.36
    Calcium
    0.36
    閨
    0.36
    杓
    0.35
     alg
    0.35
    POSITIVE LOGITS
     charming
    0.39
     driver
    0.38
    abbage
    0.37
     resumes
    0.37
     homeless
    0.36
     kelahiran
    0.36
     endorsements
    0.36
     flexible
    0.35
    bigskip
    0.35
     homeschooling
    0.35
    Activations Density 0.000%

    No Known Activations