© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 58238
    Prev
    Next
    INDEX
    Explanations

    Chinese words

    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_59_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
    吧
    2.45
    了吧
    1.36
     nhé
    1.30
    นะ
    1.00
    นะคะ
    0.96
    ですね
    0.95
     นะ
    0.92
    啦
    0.91
    นะครับ
    0.88
     nhá
    0.82
    POSITIVE LOGITS
     ventaja
    0.40
     ע
    0.38
     chemicals
    0.38
     crédito
    0.38
     banners
    0.37
     conocimiento
    0.37
     raff
    0.37
     antidepressant
    0.37
     অবস্থানে
    0.37
     drugg
    0.37
    Activations Density 0.001%

    No Known Activations