© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 193400
    Prev
    Next
    INDEX
    Explanations

    vent or ventilation systems

    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_9_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
    ियों
    0.66
    
    0.62
    偏移
    0.59
    ４
    0.57
    
    0.57
     by
    0.57
    顗
    0.56
    மாக
    0.56
    時間
    0.56
    ות
    0.55
    POSITIVE LOGITS
    ק
    0.97
    א
    0.75
    ant
    0.71
    אנ
    0.64
     película
    0.64
    ↵
    0.63
     canción
    0.61
    র
    0.61
     condição
    0.59
    that
    0.59
    Activations Density 0.000%

    No Known Activations