© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 105822
    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_1_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
     konnte
    1.18
    癀
    1.05
     deveria
    1.02
     már
    0.99
     ebbe
    0.98
     conos
    0.98
     nasceu
    0.97
     není
    0.96
     irá
    0.96
     feito
    0.95
    POSITIVE LOGITS
    ین
    1.52
    the
    1.33
    ری
    1.30
    কে
    1.27
    ٹ
    1.22
    2
    1.20
    지
    1.18
    سی
    1.17
    ت
    1.16
    ج
    1.15
    Activations Density 0.000%

    No Known Activations