© 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. 58511
    Prev
    Next
    INDEX
    Explanations

    quality control, manufacturing, industry

    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
     creer
    0.60
     "<
    0.58
     holder
    0.58
     bagel
    0.56
     khăn
    0.56
     fonctionnalité
    0.54
     flatten
    0.54
     pretzel
    0.54
     muffin
    0.54
     kullan
    0.53
    POSITIVE LOGITS
    p
    0.64
    those
    0.63
    l
    0.63
    Industry
    0.60
    i
    0.59
    industry
    0.58
    0
    0.57
    rt
    0.55
    xlim
    0.55
    localtime
    0.55
    Activations Density 0.009%

    No Known Activations