© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 140331
    Prev
    Next
    INDEX
    Explanations

    sharks

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     Fiore
    0.43
     হাদী
    0.40
     Linn
    0.39
     वृन्दावन
    0.39
     Gardening
    0.38
     causation
    0.38
    瑠
    0.37
     JavaBeans
    0.37
    acetyl
    0.37
     лигасы
    0.37
    POSITIVE LOGITS
     Shark
    3.05
     shark
    3.03
    Shark
    2.97
     sharks
    2.80
    shark
    2.75
     Sharks
    2.66
    鲨
    2.27
    鯊
    2.25
    🦈
    1.88
     샤
    1.27
    Activations Density 0.002%

    No Known Activations