© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 91727
    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_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
    ಡ
    0.58
     polymerase
    0.57
     brushless
    0.57
     neuroscience
    0.57
     mores
    0.56
    कैसे
    0.55
     alarms
    0.55
     glutamate
    0.55
    ?
    0.55
     cases
    0.55
    POSITIVE LOGITS
    iskt
    0.68
    ﻜ
    0.56
    ﺸ
    0.53
    il
    0.52
    K
    0.52
    Kau
    0.51
     Öff
    0.50
    mapped
    0.50
     Tüm
    0.50
    ﻯ
    0.50
    Activations Density 0.000%

    No Known Activations