© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 1142
    Prev
    Next
    INDEX
    Explanations

    check mark icon

    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_40_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
     Egal
    0.38
    CubeSize
    0.37
     Volume
    0.36
     Windows
    0.36
     presum
    0.36
    枺
    0.36
     Less
    0.35
    疆
    0.35
     Wikimedia
    0.35
     JPEG
    0.35
    POSITIVE LOGITS
    Check
    0.63
     check
    0.60
    check
    0.57
     Check
    0.55
    CHECK
    0.51
    检查
    0.49
     CHECK
    0.48
    chek
    0.45
     چک
    0.44
    checking
    0.43
    Activations Density 0.057%

    No Known Activations