© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175713
    Prev
    Next
    INDEX
    Explanations

    expected frequency, number, value, score

    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_20_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
     James
    0.54
     Copper
    0.52
     American
    0.51
    ↵↵
    0.49
     William
    0.48
     Times
    0.48
     Continue
    0.48
     Try
    0.47
     Welcome
    0.47
     Credit
    0.47
    POSITIVE LOGITS
     букмекер
    0.50
     প্রভাস
    0.49
    ровке
    0.48
    缥
    0.47
     карка
    0.46
    டுதல்
    0.45
    Settl
    0.45
     رکھنے
    0.45
    platinum
    0.44
    ហា
    0.44
    Activations Density 0.002%

    No Known Activations