© 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. 176376
    Prev
    Next
    INDEX
    Explanations

    foreign characters, names

    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
     ins
    0.47
     Vance
    0.42
     h
    0.37
    
    0.37
     Bet
    0.37
    Pen
    0.37
    γων
    0.37
    ુર
    0.36
     conjugated
    0.36
    Gear
    0.36
    POSITIVE LOGITS
     derece
    0.54
     Лу
    0.45
     Luigi
    0.41
     आयुर्वेदिक
    0.41
     Luch
    0.39
    吕
    0.39
    呂
    0.38
    ཀ
    0.38
    泗
    0.37
    𝘿
    0.37
    Activations Density 0.000%

    No Known Activations