© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 33520
    Prev
    Next
    INDEX
    Explanations

    explaining the purpose of each

    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
    娼
    0.37
    qp
    0.37
     inviting
    0.34
    swürdig
    0.34
    DUC
    0.33
     слоя
    0.33
     NATURAL
    0.32
     QUEST
    0.32
    嵐
    0.32
     Änder
    0.32
    POSITIVE LOGITS
     mil
    0.38
    Thomas
    0.37
     USDA
    0.35
    ichert
    0.34
    Hd
    0.34
    ว่าเป็น
    0.33
    Court
    0.32
     fonctionnalité
    0.32
    Shop
    0.32
    opia
    0.32
    Activations Density 0.004%

    No Known Activations