© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 49630
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_10_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
     нефте
    0.54
     Kan
    0.47
    вае
    0.47
     كرد
    0.46
     Kurdistan
    0.46
     Moth
    0.46
    Tiene
    0.46
    歳
    0.45
     nave
    0.44
    Collapsed
    0.43
    POSITIVE LOGITS
    cology
    0.58
    alia
    0.55
     anionic
    0.50
     seasonings
    0.50
     orientated
    0.50
    cate
    0.49
    cules
    0.49
     vides
    0.49
    bler
    0.48
    cups
    0.47
    Activations Density 0.000%

    No Known Activations