© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 130876
    Prev
    Next
    INDEX
    Explanations

    farming

    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_50_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
    াতের
    0.37
    
    0.36
    اعر
    0.36
     maked
    0.35
    ଉ
    0.34
    🚽
    0.34
    蛍光
    0.34
     ureth
    0.33
     Gabriele
    0.33
    omena
    0.33
    POSITIVE LOGITS
     Farm
    2.64
    Farm
    2.64
     farm
    2.63
     FARM
    2.52
    farm
    2.44
     farming
    2.33
     farms
    2.30
    农
    2.30
     Farms
    2.22
     Farming
    2.19
    Activations Density 0.007%

    No Known Activations