© 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. 31246
    Prev
    Next
    INDEX
    Explanations

    multilingual concepts

    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
     Unwin
    0.42
    棭
    0.37
    tpVar
    0.37
    ++;
    0.36
    added
    0.36
     kaldığımız
    0.35
     mult
    0.35
     Bajo
    0.35
    sched
    0.35
    諏
    0.35
    POSITIVE LOGITS
    都能
    0.70
     jsou
    0.68
     were
    0.67
     are
    0.66
     đều
    0.64
    都
    0.64
     можуть
    0.63
     occurs
    0.63
    都有
    0.63
    都不
    0.63
    Activations Density 0.005%

    No Known Activations