© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 5713
    Prev
    Next
    INDEX
    Explanations

    precision farming

    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_40_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
    Audio
    0.39
    Bubble
    0.37
    ltk
    0.36
     койма
    0.36
    영
    0.36
    ဦ
    0.36
    按摩
    0.36
     Association
    0.35
    Exchange
    0.35
    uidos
    0.35
    POSITIVE LOGITS
     inoc
    0.43
     planète
    0.41
     Bevölker
    0.41
    ंत्रित
    0.39
     Oren
    0.39
    痢
    0.39
     Precision
    0.38
     precis
    0.37
     رب
    0.37
     microbial
    0.37
    Activations Density 0.018%

    No Known Activations