© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 233908
    Prev
    Next
    INDEX
    Explanations

    fire

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    ayama
    0.41
     בית
    0.37
    mae
    0.37
     INIT
    0.36
    SourceName
    0.36
     سيدنا
    0.35
    沪
    0.35
     বলা
    0.35
    пля
    0.34
    淞
    0.34
    POSITIVE LOGITS
     fire
    2.75
    fire
    2.39
    火
    2.30
    Fire
    2.28
     Fire
    2.20
    FIRE
    1.94
     FIRE
    1.93
     fuego
    1.89
     fires
    1.87
     آتش
    1.80
    Activations Density 0.001%

    No Known Activations