© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 180495
    Prev
    Next
    INDEX
    Explanations

    feeling unwell or sick

    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_24_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
    ίκη
    0.40
    妙
    0.39
    ᵗ
    0.38
    ṯ
    0.37
    To
    0.37
    oncer
    0.36
    Added
    0.36
    epub
    0.36
    turquoise
    0.36
     તેમણે
    0.35
    POSITIVE LOGITS
    兇
    0.41
    飕
    0.41
     outros
    0.38
     domains
    0.36
     Essas
    0.36
     bakery
    0.36
     supre
    0.35
     Są
    0.35
    ابية
    0.35
     UEFA
    0.34
    Activations Density 0.004%

    No Known Activations