© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 117932
    Prev
    Next
    INDEX
    Explanations

    test, checked, analyzed, blood, levels, examinations

    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_27_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
     inconsc
    0.39
     asegurar
    0.38
    ZER
    0.38
     తు
    0.37
    
    0.37
    Pago
    0.37
    burgh
    0.37
    வ்
    0.37
     minggu
    0.37
     asegura
    0.37
    POSITIVE LOGITS
     reply
    0.41
     staples
    0.41
     defective
    0.41
     Temple
    0.41
     examinations
    0.41
     inexpensive
    0.41
     approved
    0.39
     temple
    0.39
    铯
    0.39
     prescription
    0.39
    Activations Density 0.004%

    No Known Activations