© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 15788
    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_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
    ธรรม
    0.35
    плы
    0.34
     कांस
    0.33
    ުގައި
    0.32
     হ্
    0.32
    Discover
    0.32
     digitalWrite
    0.32
    喟
    0.32
     আমিন
    0.31
    éssel
    0.31
    POSITIVE LOGITS
     received
    2.56
     receive
    2.38
     receb
    2.27
     receives
    2.23
    received
    2.23
    receive
    2.22
     Received
    2.22
     receiving
    2.17
     recibir
    2.16
     receber
    2.16
    Activations Density 0.148%

    No Known Activations