© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 179508
    Prev
    Next
    INDEX
    Explanations

    say "quarter"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    <0xBB>
    0.39
    ധി
    0.38
    cmd
    0.37
     Sebastián
    0.36
     thromb
    0.36
    嬉
    0.36
     pisc
    0.36
     thisComponent
    0.35
     ತಿ
    0.35
    쑥
    0.35
    POSITIVE LOGITS
    四
    1.50
    FOUR
    1.38
    Four
    1.34
     FOUR
    1.27
     четвер
    1.27
     Four
    1.27
     quart
    1.27
     quarter
    1.26
    Quarter
    1.26
     fours
    1.26
    Activations Density 0.001%

    No Known Activations