© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 79427
    Prev
    Next
    INDEX
    Explanations

    location 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_53_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
    闻
    0.41
    厉害
    0.40
     sevent
    0.39
     stok
    0.38
    awat
    0.38
    摡
    0.38
     ভারী
    0.37
    તો
    0.37
     bảy
    0.37
    เซ
    0.36
    POSITIVE LOGITS
     Ap
    0.42
     M
    0.41
    Ap
    0.40
     ofApp
    0.39
     kHz
    0.39
     Fuck
    0.39
     Plut
    0.38
    müşt
    0.38
    ;;
    0.37
    澎
    0.37
    Activations Density 0.000%

    No Known Activations