© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 100415
    Prev
    Next
    INDEX
    Explanations

    glands, udder, torch, grip, circuit, line

    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_14_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
    ရာ
    0.35
     ję
    0.35
    砚
    0.34
    鯢
    0.33
     fingert
    0.33
     معنات
    0.33
     olduğu
    0.32
     জায়গা
    0.31
    世界上
    0.31
    ულია
    0.31
    POSITIVE LOGITS
     Màu
    0.32
    ز
    0.31
     آف
    0.30
    Color
    0.29
     Dhan
    0.29
     Calibration
    0.29
     Drog
    0.29
     beh
    0.28
    color
    0.28
    یس
    0.28
    Activations Density 0.016%

    No Known Activations