© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45422
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_13_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
     Audit
    0.50
     Activation
    0.46
    现
    0.45
     Biomedical
    0.45
     Tach
    0.43
     Petroleum
    0.43
    简介
    0.43
    allows
    0.43
    来自
    0.43
     General
    0.42
    POSITIVE LOGITS
    isola
    0.54
    :[/
    0.52
     इन्
    0.49
     สอบ
    0.48
     жаңы
    0.48
     まあ
    0.46
     инженер
    0.46
    Atoi
    0.46
     mexico
    0.46
     специ
    0.45
    Activations Density 0.000%

    No Known Activations