© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 224057
    Prev
    Next
    INDEX
    Explanations

    medication

    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_10_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
     drug
    0.27
     sociaux
    0.25
     numb
    0.23
    Drug
    0.23
    Р
    0.23
    iam
    0.22
    |
    0.22
     fibr
    0.22
     doctor
    0.22
    ది
    0.22
    POSITIVE LOGITS
    arza
    0.29
    lari
    0.28
    mybatis
    0.27
    ारी
    0.27
     Arz
    0.27
    lös
    0.26
    ியை
    0.26
     Será
    0.26
    妵
    0.25
    époque
    0.25
    Activations Density 0.006%

    No Known Activations