© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 78801
    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_53_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
     Simons
    0.42
    ucks
    0.41
     Тур
    0.41
     attainable
    0.39
     timeCounter
    0.39
     Sora
    0.38
    Gc
    0.38
    嵊
    0.38
    inosaur
    0.38
     SX
    0.38
    POSITIVE LOGITS
     benar
    0.42
    댑
    0.38
    LEN
    0.38
    codegen
    0.37
    Kenn
    0.36
    真
    0.36
     처
    0.34
     veri
    0.34
     ken
    0.33
    ken
    0.33
    Activations Density 0.000%

    No Known Activations