© 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. 2765
    Prev
    Next
    INDEX
    Explanations

    INSERT INTO

    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
     Sixteen
    0.38
     Bucc
    0.35
    
    0.35
    十六
    0.34
    ᕗ
    0.34
     प्रेरित
    0.34
    Hood
    0.34
     Studium
    0.34
     BC
    0.33
     sixteenth
    0.33
    POSITIVE LOGITS
    ँग
    0.42
    Removed
    0.38
     spindle
    0.37
    럴
    0.35
    remove
    0.34
    খাল
    0.34
    refer
    0.34
    concurrent
    0.34
     করপোর
    0.34
    Fruits
    0.34
    Activations Density 0.044%

    No Known Activations