© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 21002
    Prev
    Next
    INDEX
    Explanations

    instance

    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_56_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
     demonstrating
    0.40
     worn
    0.39
     mang
    0.38
     aff
    0.37
     fuentes
    0.35
    InstrumentedTest
    0.35
     demonstrates
    0.35
    ">-->
    0.35
    ponen
    0.34
    طلاب
    0.34
    POSITIVE LOGITS
     instance
    2.45
    instance
    2.20
     instances
    2.16
    实例
    2.11
     Instance
    2.05
    Instance
    1.98
    instances
    1.87
     Instances
    1.86
     instância
    1.73
     instancia
    1.70
    Activations Density 0.276%

    No Known Activations