© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 12591
    Prev
    Next
    INDEX
    Explanations

    medical advice

    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_40_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
     케
    0.06
    istaa
    0.06
    聞いて
    0.06
     stile
    0.06
    শনে
    0.06
     (‘
    0.06
     Leibn
    0.06
     :#
    0.06
    ওয়ার্ড
    0.05
    órc
    0.05
    POSITIVE LOGITS
     Cou
    0.07
     Cohen
    0.06
     Theatre
    0.06
    cou
    0.06
     Channels
    0.06
     School
    0.06
     Life
    0.06
     Health
    0.06
     Monaco
    0.06
     ভেতরে
    0.06
    Activations Density 1.464%

    No Known Activations