© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 45459
    Prev
    Next
    INDEX
    Explanations

    JSON keys followed by colon

    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_3_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
    的代码
    0.69
     on
    0.63
     durchgeführt
    0.61
    ில்
    0.58
    ového
    0.57
    ালে
    0.55
     प्रश्‍न
    0.55
    뒀
    0.55
    ার
    0.55
     발생하는
    0.54
    POSITIVE LOGITS
    ك
    0.93
    p
    0.81
    ই
    0.73
    sh
    0.73
    ke
    0.73
    1
    0.73
    Changes
    0.72
    서
    0.72
    In
    0.70
    AY
    0.70
    Activations Density 0.001%

    No Known Activations