© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 91614
    Prev
    Next
    INDEX
    Explanations

    vinyl, laminate, flooring, tile

    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
    ö
    0.39
    生活
    0.35
     postcards
    0.35
     liv
    0.34
    atori
    0.34
    lak
    0.34
     suck
    0.33
     C
    0.33
    ↵
    0.33
     life
    0.32
    POSITIVE LOGITS
    зовая
    0.39
    Qualifier
    0.38
    іл
    0.38
     ลง
    0.38
     ВО
    0.38
    눴
    0.38
    
    0.38
     други
    0.38
     제거
    0.37
     называется
    0.37
    Activations Density 0.003%

    No Known Activations