© 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. 2735
    Prev
    Next
    INDEX
    Explanations

    government departments and agencies

    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
     梅
    0.40
    дик
    0.38
     loadAnimation
    0.37
    皮革
    0.36
    RFQ
    0.35
    erdem
    0.35
    畳
    0.35
    🥞
    0.35
     нем
    0.35
    梅
    0.35
    POSITIVE LOGITS
     Commerce
    0.82
    Commerce
    0.77
     commerce
    0.74
    commerce
    0.63
     कॉमर्स
    0.57
     परिवहन
    0.52
     Department
    0.52
     comercio
    0.51
     HHS
    0.50
     Dept
    0.47
    Activations Density 0.035%

    No Known Activations