© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 200407
    Prev
    Next
    INDEX
    Explanations

    respiratory system, nose, throat, airways

    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_37_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
     noses
    1.20
     nose
    1.19
     Nose
    0.96
    鼻子
    0.93
    鼻
    0.91
    nose
    0.89
     nariz
    0.89
     nasal
    0.79
    👃
    0.77
     नाक
    0.72
    POSITIVE LOGITS
    句
    0.38
     Meghna
    0.38
     הסי
    0.37
    രിക്കുന്ന
    0.37
     voiced
    0.37
    டா
    0.35
    ємо
    0.35
    ველი
    0.35
     നേര
    0.34
    嗐
    0.34
    Activations Density 0.024%

    No Known Activations