© 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. 50709
    Prev
    Next
    INDEX
    Explanations

    Premier League

    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
     BACH
    0.44
     Turnier
    0.42
    Donor
    0.42
    லோச
    0.41
     inputted
    0.41
    淝
    0.40
     输入
    0.39
    地域
    0.39
     आईपी
    0.39
    HASH
    0.39
    POSITIVE LOGITS
     paint
    0.40
     Momentum
    0.39
    burne
    0.36
     vibr
    0.36
     woodwork
    0.36
     Robin
    0.36
     destructive
    0.36
    破坏
    0.36
     momentum
    0.35
    [
    0.35
    Activations Density 0.024%

    No Known Activations