© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 217220
    Prev
    Next
    INDEX
    Explanations

    little/slight negative qualifiers

    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
     moeil
    0.35
     harder
    0.33
    痪
    0.32
    fielder
    0.31
     ನೀ
    0.31
    itif
    0.31
     দেবী
    0.30
    чего
    0.29
    lestage
    0.29
     하는데
    0.29
    POSITIVE LOGITS
     पीडी
    0.32
     Spirit
    0.32
    養
    0.31
     Entrepreneurs
    0.31
     kN
    0.31
     MBA
    0.29
     Tanzania
    0.29
     रुग्
    0.29
     Quinn
    0.29
     Potassium
    0.29
    Activations Density 0.011%

    No Known Activations