© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 259343
    Prev
    Next
    INDEX
    Explanations

    regulations and compliance

    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_22_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
    igt
    0.40
     Selatan
    0.37
    肴
    0.36
     সম্ভাব্য
    0.36
    enne
    0.35
     Cradle
    0.35
     खरी
    0.34
    infra
    0.34
     Sumber
    0.33
    ﹞
    0.33
    POSITIVE LOGITS
     pavilions
    0.40
    タブ
    0.38
     marched
    0.37
     marching
    0.36
    PROTON
    0.36
     chests
    0.36
    setOnAction
    0.35
     consignment
    0.35
    Alb
    0.35
     expulsion
    0.34
    Activations Density 0.005%

    No Known Activations