© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 260850
    Prev
    Next
    INDEX
    Explanations

    Hypersensitivity reaction or syndrome

    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_5_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
    It
    1.63
    ת
    1.60
    ↵↵
    1.59
    ।
    1.45
    December
    1.35
    January
    1.34
    ם
    1.33
    RO
    1.31
    June
    1.30
    February
    1.29
    POSITIVE LOGITS
    s
    1.41
    spannung
    1.21
    in
    1.14
    nung
    1.10
     inhaling
    1.07
     मनाने
    1.02
    ómica
    1.02
    ancer
    1.00
    rin
    0.99
    rés
    0.98
    Activations Density 0.005%

    No Known Activations