© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 80708
    Prev
    Next
    INDEX
    Explanations

    Returns a value

    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_31_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
     quietly
    0.28
    ्यूशन
    0.26
     incidentally
    0.26
    tau
    0.26
    叽
    0.25
     అమలు
    0.25
    ionalmente
    0.24
    䢍
    0.24
    利用者
    0.24
    न्दावन
    0.24
    POSITIVE LOGITS
     Void
    0.34
     Teeth
    0.31
     Lum
    0.30
     Sole
    0.29
     Carbohyd
    0.29
    วล
    0.28
     desires
    0.28
     medulla
    0.28
     Để
    0.28
     Thương
    0.27
    Activations Density 0.013%

    No Known Activations