© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 39530
    Prev
    Next
    INDEX
    Explanations

    East Asian names

    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_57_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
    Chen
    0.49
     चेन
    0.47
    李
    0.46
     Lee
    0.45
    Lee
    0.44
     LEE
    0.43
     Lipschitz
    0.43
     lee
    0.42
    チャン
    0.42
     Inoue
    0.42
    POSITIVE LOGITS
     X
    0.47
     Qa
    0.45
     Bu
    0.44
     Dred
    0.44
     Sad
    0.43
     QV
    0.40
     Mus
    0.39
     Sid
    0.38
     Salam
    0.38
    Salam
    0.38
    Activations Density 0.001%

    No Known Activations