© 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. 32058
    Prev
    Next
    INDEX
    Explanations

    acronyms and initialisms

    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
    Dod
    0.39
     चाहि
    0.38
    Hz
    0.37
     Dod
    0.37
    Hers
    0.37
    ^{-
    0.36
    hasClass
    0.36
     Henn
    0.36
     Hate
    0.36
     Domains
    0.36
    POSITIVE LOGITS
     Kimura
    0.50
    囷
    0.41
     maest
    0.40
    বাক
    0.40
     viande
    0.40
    ZY
    0.39
     玄
    0.39
     للمع
    0.39
    appa
    0.38
    BSC
    0.38
    Activations Density 0.002%

    No Known Activations