© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 52388
    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_55_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
     cellspacing
    0.39
     intakes
    0.36
    iggio
    0.34
    leau
    0.33
     Bones
    0.33
    낌
    0.33
    icker
    0.33
    ូវ
    0.32
    obb
    0.31
     deposition
    0.31
    POSITIVE LOGITS
     fire
    3.52
    fire
    2.98
    Fire
    2.89
    火
    2.89
     Fire
    2.80
     FIRE
    2.41
    FIRE
    2.36
     फायर
    2.20
     fuego
    2.17
     fires
    2.08
    Activations Density 0.047%

    No Known Activations