© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 50420
    Prev
    Next
    INDEX
    Explanations

    say "by"

    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_55_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
    ᅩ
    0.34
    万元
    0.33
     ويكي
    0.33
    晗
    0.32
    璞
    0.32
     URANIUM
    0.32
     kN
    0.31
    滹
    0.31
    endaft
    0.31
     लिहा
    0.31
    POSITIVE LOGITS
    BY
    2.95
     BY
    2.91
     Byron
    2.89
     Bye
    2.47
     бы
    2.44
     bye
    2.44
    By
    2.41
     Byrne
    2.41
     Byl
    2.39
     Бы
    2.38
    Activations Density 0.061%

    No Known Activations