© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 32613
    Prev
    Next
    INDEX
    Explanations

    Inflammatory Bowel Disease (IBD)

    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_31_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
     Ñ
    0.45
    ஷ்ய
    0.39
    ドイツ
    0.39
    virtual
    0.38
     Plex
    0.37
     Mạnh
    0.37
     Германии
    0.37
     জার
    0.37
    碟
    0.37
     Ex
    0.37
    POSITIVE LOGITS
    педия
    0.45
     cruising
    0.42
    nelles
    0.40
     flooring
    0.38
     taza
    0.38
    érale
    0.38
    ographics
    0.37
    anyard
    0.36
     cruises
    0.36
     pieds
    0.36
    Activations Density 0.002%

    No Known Activations