© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 145587
    Prev
    Next
    INDEX
    Explanations

    patient medical context

    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_0_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
    し
    1.80
    t
    1.70
    ing
    1.58
    する
    1.47
    ו
    1.47
    en
    1.38
    n
    1.38
    ή
    1.34
    و
    1.27
     powied
    1.25
    POSITIVE LOGITS
     in
    1.98
    ك
    1.82
    ES
    1.73
    ED
    1.73
    OT
    1.63
    ট
    1.62
    AD
    1.59
    .
    1.49
    ER
    1.45
     accolades
    1.43
    Activations Density 0.001%

    No Known Activations