© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 133866
    Prev
    Next
    INDEX
    Explanations

    loss of taste or smell

    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
    Negative Logits
    
    0.42
    ገድ
    0.38
    cab
    0.37
     reflectivity
    0.37
    
    0.36
     وړ
    0.36
    㖩
    0.36
     fleece
    0.35
     asset
    0.35
    conversation
    0.35
    POSITIVE LOGITS
     taste
    1.02
    Taste
    0.95
     Taste
    0.93
    嗅
    0.88
     smell
    0.88
     вку
    0.82
     smak
    0.82
     smells
    0.81
     вкус
    0.80
    taste
    0.80
    Activations Density 0.004%

    No Known Activations