© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 18215
    Prev
    Next
    INDEX
    Explanations

    main() function calls

    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_15_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
    ଣ
    0.15
    llo
    0.14
    site
    0.13
    birth
    0.13
    isar
    0.13
    lal
    0.12
    iculture
    0.12
    nal
    0.12
     एनसी
    0.12
    zoned
    0.12
    POSITIVE LOGITS
     processo
    0.17
    ﻊ
    0.14
    
    0.13
     جيد
    0.13
     proposito
    0.13
    ﻌ
    0.13
     процес
    0.13
    F
    0.13
     процессе
    0.13
     carta
    0.13
    Activations Density 0.007%

    No Known Activations