© 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. 155245
    Prev
    Next
    INDEX
    Explanations

    diverse languages/terms

    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
     hurd
    0.44
     আবির্ভাব
    0.39
    дук
    0.39
     Unlike
    0.37
    泮
    0.36
     Проци
    0.36
     peeling
    0.36
     Strikes
    0.35
     Ảnh
    0.34
    findOrFail
    0.34
    POSITIVE LOGITS
    क्त
    0.42
     sy
    0.40
    стая
    0.39
    zhen
    0.39
    atsiya
    0.39
    Chev
    0.38
    ത്തിന്റെയും
    0.38
    譯
    0.38
    
    0.37
     asset
    0.36
    Activations Density 0.005%

    No Known Activations