© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 237775
    Prev
    Next
    INDEX
    Explanations

    contact point

    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_32_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
     lefty
    0.68
     Left
    0.57
    LEFT
    0.57
     LEFT
    0.57
    右手
    0.57
    Left
    0.56
     왼
    0.54
    利き
    0.54
     left
    0.53
     RIGHT
    0.50
    POSITIVE LOGITS
     giữ
    0.47
     bik
    0.40
    保留
    0.39
     utrzym
    0.39
     tub
    0.38
     keeps
    0.38
     حفظ
    0.37
     menjaga
    0.36
     насо
    0.36
     submanifold
    0.36
    Activations Density 0.005%

    No Known Activations