© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 61964
    Prev
    Next
    INDEX
    Explanations

    DHIS2, NHIS, health data systems

    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_2_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
    ת
    1.50
     rozpoczę
    1.41
    ید
    1.35
     przyję
    1.30
     arrivé
    1.21
    。
    1.16
    ุ
    1.13
    টি
    1.13
     storica
    1.13
     pubblici
    1.12
    POSITIVE LOGITS
    (
    1.21
    /
    1.17
    <0x0D>
    1.13
    $
    1.12
    {
    1.08
    ("/
    1.03
     are
    1.01
    ts
    0.95
    jha
    0.94
    you
    0.93
    Activations Density 0.000%

    No Known Activations