© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 38112
    Prev
    Next
    INDEX
    Explanations

    red blood cells or cell sedimentation

    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_11_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
     Seç
    0.61
     Freem
    0.57
    æ
    0.57
     Tüm
    0.56
    İ
    0.55
     Spes
    0.53
     Typing
    0.53
     Ş
    0.52
    స్
    0.51
     Merck
    0.51
    POSITIVE LOGITS
     देती
    0.52
     വ്യാപ
    0.52
     onError
    0.50
     deal
    0.49
    แล
    0.49
     '\\;'
    0.49
     或
    0.47
    ExceptionHandler
    0.46
     retailer
    0.46
     dispenser
    0.46
    Activations Density 0.021%

    No Known Activations