© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 17599
    Prev
    Next
    INDEX
    Explanations

    include/import/use statements

    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
     привет
    0.55
    acja
    0.55
     اگر
    0.54
     ս
    0.54
     إذا
    0.52
     و
    0.51
    ').':
    0.51
    }\,\
    0.50
     Daryl
    0.50
    ation
    0.50
    POSITIVE LOGITS
    특히
    0.55
     adhesives
    0.51
     especially
    0.50
     antibodies
    0.48
     antimicrobial
    0.48
    enges
    0.47
     특히
    0.47
     Particularly
    0.47
     Sinne
    0.47
     Büro
    0.47
    Activations Density 0.002%

    No Known Activations