© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 48756
    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
     לח
    0.50
    '
    0.50
     نظر
    0.47
    घात
    0.45
    gruppen
    0.45
    raum
    0.44
     brigade
    0.44
    rob
    0.43
    fstream
    0.43
     प्रयोग
    0.42
    POSITIVE LOGITS
     cytokines
    0.51
     tío
    0.48
     convertido
    0.47
    ש
    0.47
     Lewis
    0.47
     tercero
    0.46
    ন
    0.46
     cuero
    0.46
    зво
    0.46
    ρθ
    0.46
    Activations Density 0.000%

    No Known Activations