© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214839
    Prev
    Next
    INDEX
    Explanations

    medical imaging ultrasound

    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_5_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
    s
    1.38
    ี
    1.30
    ти
    1.23
    ли
    1.19
    ์
    1.09
    า
    1.07
     Abgerufen
    1.04
    েরও
    1.04
    ы
    1.04
    <h4>
    1.03
    POSITIVE LOGITS
    {
    1.47
    an
    1.25
    ación
    1.13
    -
    0.95
    ul
    0.94
    ión
    0.94
    spiration
    0.93
    <0x93>
    0.91
    inį
    0.91
    isión
    0.90
    Activations Density 0.000%

    No Known Activations