© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 126
    Prev
    Next
    INDEX
    Explanations

    Open a terminal

    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
    oplasty
    0.43
    纭
    0.39
    䣬
    0.39
    orrhea
    0.37
     आशी
    0.36
     cornea
    0.36
     дисципли
    0.36
     न्याय
    0.36
    レザー
    0.36
     சந்திர
    0.36
    POSITIVE LOGITS
     Ljub
    0.43
     Terminal
    0.42
    挙
    0.40
     Firefox
    0.40
    Terminal
    0.39
    accessory
    0.38
    firefox
    0.38
     firefox
    0.38
    Accessories
    0.38
     accessories
    0.38
    Activations Density 0.009%

    No Known Activations