© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 161934
    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_31_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
    มิ
    0.40
     режи
    0.40
     Jackie
    0.40
    Jackie
    0.39
     クリア
    0.38
    捡
    0.38
    정한
    0.38
     Sasha
    0.38
     впечатление
    0.37
     legge
    0.37
    POSITIVE LOGITS
     quibusdam
    0.38
    趸
    0.38
     vorticity
    0.37
    quium
    0.37
    псо
    0.37
     guessing
    0.36
     সমাবেশে
    0.36
     zus
    0.36
     nomenclatura
    0.36
    isia
    0.35
    Activations Density 0.000%

    No Known Activations