© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 32381
    Prev
    Next
    INDEX
    Explanations

    UUID generation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
     уника
    0.48
     लॉन्ग
    0.42
    ว์
    0.41
     longo
    0.41
     Unique
    0.40
     long
    0.40
     uniquely
    0.40
    长
    0.40
    长期
    0.39
     زنج
    0.38
    POSITIVE LOGITS
    CIF
    0.41
     signific
    0.41
     Buf
    0.41
     Oven
    0.40
    庣
    0.39
     আর্কাইভ
    0.39
     CIF
    0.38
    τικά
    0.37
    rates
    0.37
     Ashe
    0.36
    Activations Density 0.001%

    No Known Activations