© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 6828
    Prev
    Next
    INDEX
    Explanations

    smell and odor

    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_40_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
    untza
    0.39
     (<
    0.37
    ations
    0.37
    ට්
    0.35
    വാ
    0.34
     taff
    0.34
    プション
    0.33
    ἄ
    0.33
    ését
    0.33
     dilwale
    0.32
    POSITIVE LOGITS
     smell
    0.89
     smells
    0.87
     odors
    0.81
     pleasant
    0.76
     odor
    0.75
     запах
    0.74
     aromas
    0.73
     aroma
    0.72
     scents
    0.71
     неприят
    0.71
    Activations Density 0.123%

    No Known Activations