© 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-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1702
    Prev
    Next
    INDEX
    Explanations

    mentions of farming, land use, and conservation

    oai_token-act-pair · gemini-2.0-flash

    farming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     farm
    -1.89
     Farm
    -1.73
    Farm
    -1.71
    farm
    -1.68
     farms
    -1.67
     FARM
    -1.61
     farmer
    -1.57
     farming
    -1.56
     Farms
    -1.54
    farms
    -1.52
    POSITIVE LOGITS
    RegistryLite
    0.48
    ونت
    0.44
     horaire
    0.44
     chré
    0.43
    addTab
    0.42
     identifiés
    0.41
     rosse
    0.40
    +#+#
    0.39
     bira
    0.39
     détru
    0.39
    Activations Density 2.056%

    No Known Activations