© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 179202
    Prev
    Next
    INDEX
    Explanations

    medical and institutional information

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     James
    0.44
    James
    0.44
    Bass
    0.43
    慮
    0.41
    JAMES
    0.41
     Bas
    0.38
    Priority
    0.38
    ͜
    0.37
     Wil
    0.36
    นั่ง
    0.36
    POSITIVE LOGITS
     zod
    0.40
    ቪ
    0.39
     बढ़त
    0.38
     ascorbic
    0.38
     Verlust
    0.37
    ობ
    0.37
     fragility
    0.36
     அலெக்ஸாண்ட்
    0.36
     Oph
    0.36
     zenith
    0.36
    Activations Density 0.001%

    No Known Activations