© 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. 10283
    Prev
    Next
    INDEX
    Explanations

    `if [ condition ]` or `[ condition test]`

    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_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
     بناء
    0.50
    改革
    0.47
    を作成
    0.47
    טורק
    0.46
    家用
    0.46
     製
    0.46
    reni
    0.46
    你會
    0.46
    UAE
    0.46
     歩
    0.45
    POSITIVE LOGITS
     rak
    0.57
    цем
    0.51
     spal
    0.48
     bez
    0.48
    iju
    0.48
     hood
    0.47
    ່ມ
    0.47
    ิศ
    0.46
     Fru
    0.46
     juices
    0.46
    Activations Density 0.086%

    No Known Activations