© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 201983
    Prev
    Next
    INDEX
    Explanations

    fire-resistant materials or ratings

    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_37_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
     entidade
    0.37
    鹤
    0.37
     Enter
    0.37
    ↵
    0.36
    Enter
    0.36
    บรร
    0.36
     publisher
    0.34
     columns
    0.34
     undefined
    0.34
    publisher
    0.34
    POSITIVE LOGITS
     পঞ্চ
    0.45
    投資
    0.43
     Вікі
    0.40
    াহার
    0.39
     penet
    0.39
     बैच
    0.39
     penetrates
    0.39
    odat
    0.38
    切
    0.38
    hole
    0.38
    Activations Density 0.011%

    No Known Activations