© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 164201
    Prev
    Next
    INDEX
    Explanations

    nylon or polyester

    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_31_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
     metals
    0.40
     utens
    0.39
    內
    0.39
     internals
    0.38
     Metals
    0.37
    toare
    0.37
     ሕ
    0.37
     nontrivial
    0.37
     fruits
    0.37
     thistle
    0.37
    POSITIVE LOGITS
     विक्रय
    0.40
     ضعف
    0.39
     моби
    0.38
     sprzed
    0.37
     販売
    0.37
     unst
    0.36
     максимально
    0.36
    
    0.36
     Schu
    0.35
     Рим
    0.35
    Activations Density 0.000%

    No Known Activations