© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 196252
    Prev
    Next
    INDEX
    Explanations

    wedgie

    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_4_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
    ため
    0.86
    的车
    0.84
    的处理
    0.83
    il
    0.82
    人
    0.82
    on
    0.79
    ipients
    0.78
    的选择
    0.77
    會有
    0.76
    的他
    0.76
    POSITIVE LOGITS
    ם
    1.15
    י
    1.13
    د
    1.05
     for
    1.02
    ד
    0.98
    ي
    0.94
    ри
    0.86
     של
    0.84
    س
    0.84
     Guant
    0.84
    Activations Density 0.000%

    No Known Activations