© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 197818
    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_50_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
     Mont
    0.41
    Mont
    0.39
    廷
    0.39
     Thirty
    0.39
     आगरा
    0.38
    Slim
    0.38
    ادل
    0.37
     اتش
    0.36
     메
    0.35
    зывать
    0.35
    POSITIVE LOGITS
     repress
    0.50
    婊
    0.40
    ariance
    0.39
     algunas
    0.38
     richness
    0.38
     secs
    0.38
    依頼
    0.38
    鑄
    0.38
     Rupp
    0.37
    ndez
    0.37
    Activations Density 0.000%

    No Known Activations