© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 37215
    Prev
    Next
    INDEX
    Explanations

    foreign words

    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
    Negative Logits
    生死
    0.40
    ያው
    0.39
     Authentic
    0.38
    師
    0.38
     Dressing
    0.35
    mingw
    0.35
    eseorang
    0.35
    其中包括
    0.35
    owa
    0.35
    influenced
    0.34
    POSITIVE LOGITS
     Cá
    0.38
    များနှင့်
    0.38
     Zas
    0.37
     sẵn
    0.37
    тента
    0.37
     পরি
    0.36
    Cs
    0.36
    𒉿
    0.36
     здо
    0.35
    ]')
    0.35
    Activations Density 0.011%

    No Known Activations