© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 227371
    Prev
    Next
    INDEX
    Explanations

    World Health Organization

    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_6_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
    你
    1.14
    ేక
    1.02
    মতী
    0.98
    ١
    0.98
     preocupación
    0.94
    સ્ટ
    0.92
    ولي
    0.92
    的的
    0.92
    此
    0.91
    两
    0.91
    POSITIVE LOGITS
    '
    1.66
    {
    1.00
    (
    0.96
    h
    0.93
    ş
    0.93
    0
    0.91
    ‘
    0.88
    -
    0.88
    j
    0.87
     \
    0.85
    Activations Density 0.000%

    No Known Activations