© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 63755
    Prev
    Next
    INDEX
    Explanations

    tile and flooring installation

    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_41_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
    格納
    0.46
     spray
    0.44
    spray
    0.41
    urea
    0.41
     poly
    0.41
     Spray
    0.41
    脲
    0.39
    SPRAY
    0.39
    ıcı
    0.38
     Plantation
    0.38
    POSITIVE LOGITS
     Cement
    0.40
    🅰
    0.40
     cement
    0.39
     wedi
    0.38
     Oke
    0.38
    cement
    0.38
     Koles
    0.38
     कंपाउंड
    0.37
     surrounding
    0.37
    Oss
    0.37
    Activations Density 0.001%

    No Known Activations