© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 173548
    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_20_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
    ારે
    0.51
     আজাদ
    0.51
    數量
    0.50
    醝
    0.49
    Jumlah
    0.48
    meros
    0.47
    rlig
    0.47
     Quil
    0.47
     сравни
    0.45
    焉
    0.44
    POSITIVE LOGITS
     demonstrate
    0.51
     demonstrated
    0.49
     vessel
    0.48
     demonstrates
    0.48
     fiery
    0.47
     artery
    0.46
     television
    0.46
     ship
    0.45
     intrusion
    0.44
     minh
    0.44
    Activations Density 0.000%

    No Known Activations