© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 11708
    Prev
    Next
    INDEX
    Explanations

    refactor and analyze code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
     shortcut
    0.38
    延
    0.36
    する方法
    0.35
    shortcut
    0.35
     gezeigt
    0.34
     verbinden
    0.33
    ombok
    0.32
    лән
    0.32
    zentration
    0.32
    ({});
    0.32
    POSITIVE LOGITS
    Analyze
    0.39
     cati
    0.39
     Analyze
    0.38
     анализа
    0.38
    тына
    0.38
    Analysis
    0.37
     Analysis
    0.37
    illet
    0.35
     Analy
    0.35
    ivided
    0.35
    Activations Density 0.002%

    No Known Activations