© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 33678
    Prev
    Next
    INDEX
    Explanations

    shared preferences

    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
    Negative Logits
     alleging
    0.41
     النص
    0.41
    тету
    0.41
     obtiene
    0.39
    平台的
    0.39
     recalc
    0.39
     Bunn
    0.37
    윕
    0.37
     애플
    0.36
     업무
    0.36
    POSITIVE LOGITS
     cleaner
    0.41
     MongoClient
    0.37
    propan
    0.37
     customPlot
    0.35
     colder
    0.35
     declar
    0.35
    Mve
    0.35
     requirement
    0.34
     qo
    0.34
     innovator
    0.34
    Activations Density 0.000%

    No Known Activations