© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 239095
    Prev
    Next
    INDEX
    Explanations

    medical records and charts

    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_25_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
    纳
    0.39
     expressed
    0.38
    Perry
    0.38
    ﾎ
    0.38
    ﾅ
    0.38
    ંબા
    0.37
    romes
    0.37
    ‏
    0.37
    ﾒ
    0.37
    িনা
    0.36
    POSITIVE LOGITS
     специали
    0.42
     kred
    0.41
     구축
    0.41
     Northampton
    0.41
     Almanya
    0.40
     Scotland
    0.39
     கதாபா
    0.39
     Suzhou
    0.39
     Poland
    0.38
     functioning
    0.38
    Activations Density 0.001%

    No Known Activations