© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 31627
    Prev
    Next
    INDEX
    Explanations

    ability of or to

    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_7_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
     เพิ่ม
    0.31
     by
    0.28
     O
    0.28
    ↵↵↵
    0.28
     AFTER
    0.28
     not
    0.27
     ควร
    0.27
    ↵↵
    0.27
     D
    0.26
     after
    0.26
    POSITIVE LOGITS
    ۔
    0.32
    л
    0.32
    ၢ
    0.31
    ا۔
    0.29
    ان
    0.28
    ціа
    0.28
    ئے۔
    0.27
    مم
    0.27
    comme
    0.27
    ร
    0.27
    Activations Density 0.001%

    No Known Activations