© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 102928
    Prev
    Next
    INDEX
    Explanations

    Medical terms

    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_16_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
     perceiving
    0.49
    ７
    0.49
    ati
    0.48
    ě
    0.48
     esetben
    0.46
    бр
    0.46
    bě
    0.45
    ảy
    0.45
    ｔ
    0.45
     requesting
    0.45
    POSITIVE LOGITS
     тебя
    0.51
     तुम
    0.50
     عليك
    0.49
    امة
    0.48
     სხვა
    0.47
     Automobile
    0.47
    ive
    0.46
    anza
    0.46
     Sake
    0.46
     Accompl
    0.46
    Activations Density 0.000%

    No Known Activations