© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 33052
    Prev
    Next
    INDEX
    Explanations

    multi-lingual text fragments

    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
    ilib
    0.44
     Latitude
    0.40
     fio
    0.40
    sdk
    0.39
     ވަ
    0.38
    龜
    0.38
    ミノ
    0.38
     Би
    0.38
    悖
    0.37
     שב
    0.37
    POSITIVE LOGITS
    Unary
    0.38
     paused
    0.37
     বাসিন্দা
    0.35
    ლა
    0.35
    ጠት
    0.35
    姐
    0.35
    
    0.35
    GoalState
    0.34
     run
    0.34
    zag
    0.34
    Activations Density 0.003%

    No Known Activations