© 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. 7348
    Prev
    Next
    INDEX
    Explanations

    names that are trendy or popular

    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
    ೆಯೇ
    0.37
    kunde
    0.36
    లె
    0.36
    iggers
    0.35
    ബന്ധ
    0.35
    রদ্ব
    0.35
    aculate
    0.35
    🤚
    0.34
     Eclipse
    0.34
     collim
    0.34
    POSITIVE LOGITS
     nn
    0.52
     NN
    0.45
    nn
    0.43
    θούν
    0.43
     trendy
    0.43
    Trendy
    0.42
     middle
    0.41
    NN
    0.41
    Ph
    0.40
    middle
    0.40
    Activations Density 0.197%

    No Known Activations