© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 205864
    Prev
    Next
    INDEX
    Explanations

    patient safety, medical commissions, regulations

    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_37_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
     beds
    1.14
     bed
    1.13
    beds
    0.99
    bed
    0.96
     बिस्तर
    0.93
     Beds
    0.92
    床
    0.89
     giường
    0.89
    Bed
    0.88
     बेड
    0.83
    POSITIVE LOGITS
     taxon
    0.43
    ópolis
    0.40
    smile
    0.38
     приветствую
    0.37
    taxon
    0.37
     Державний
    0.37
     செல்
    0.37
     willkommen
    0.37
     Thế
    0.36
    썩
    0.36
    Activations Density 0.000%

    No Known Activations