© 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. 162569
    Prev
    Next
    INDEX
    Explanations

    look reveals

    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_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
    вос
    0.36
    感受
    0.34
    ]("
    0.33
    っぱ
    0.30
     Kupp
    0.30
    ]">
    0.30
    Still
    0.30
     мед
    0.30
    诠
    0.30
    になった
    0.29
    POSITIVE LOGITS
     Pipelines
    0.38
    式的
    0.37
    yne
    0.36
    历史上
    0.36
     Pump
    0.35
     trafficking
    0.35
    렁
    0.35
     pipelines
    0.34
     çıkart
    0.34
     cashier
    0.33
    Activations Density 0.002%

    No Known Activations