© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 204167
    Prev
    Next
    INDEX
    Explanations

    periods of time

    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_37_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
     Life
    0.39
    Life
    0.39
     life
    0.38
    年在
    0.37
    life
    0.37
    戤
    0.36
    過ご
    0.36
    ヒ
    0.35
    離開
    0.34
    เรียก
    0.34
    POSITIVE LOGITS
     ন্যায্য
    0.38
     Businessman
    0.38
     இருந்தார்
    0.36
     concluded
    0.35
     каме
    0.35
     Deformation
    0.35
     tierras
    0.35
     deformation
    0.35
    verson
    0.34
    CLUDE
    0.34
    Activations Density 0.001%

    No Known Activations