© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 3718
    Prev
    Next
    INDEX
    Explanations

    body health and actions

    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_39_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
    ർഷ
    0.42
    UGIN
    0.40
    %{
    0.39
    #$%
    0.37
    proofing
    0.37
    ประชา
    0.36
     انتقال
    0.35
    DOCUMENT
    0.35
     metastability
    0.35
    丐
    0.35
    POSITIVE LOGITS
     kroppen
    0.77
     body
    0.76
     tubuh
    0.75
     الجسم
    0.74
     cuerpo
    0.72
     Body
    0.70
     शरीर
    0.70
     bodies
    0.67
    body
    0.66
    身体
    0.66
    Activations Density 0.142%

    No Known Activations