© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 1676
    Prev
    Next
    INDEX
    Explanations

    Elasticsearch DSL query

    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_40_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
    integration
    0.45
     integration
    0.43
     integración
    0.42
    펠
    0.40
    Principles
    0.39
     micro
    0.39
     Integration
    0.39
     integrations
    0.38
     principle
    0.38
     montage
    0.38
    POSITIVE LOGITS
    ร้าง
    0.42
    㹮
    0.39
     REQUEST
    0.38
    platinum
    0.38
     juniper
    0.38
     Acres
    0.37
    )}"
    0.37
    诘
    0.37
    ब्ल्यू
    0.37
     পলা
    0.37
    Activations Density 0.000%

    No Known Activations