© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10134
    Prev
    Next
    INDEX
    Explanations

    words related to soil and gardening

    oai_token-act-pair · gemini-2.0-flash

    soil conditions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Soil
    -1.62
     soil
    -1.59
    Soil
    -1.50
    soil
    -1.47
     SOIL
    -1.45
     soils
    -1.34
    SOIL
    -1.29
     Soils
    -1.25
    Soils
    -1.15
    土壤
    -1.02
    POSITIVE LOGITS
     indépend
    0.50
     humanas
    0.48
     murni
    0.46
     acrylique
    0.46
     latar
    0.45
     peup
    0.45
    érales
    0.44
     noires
    0.44
    topbar
    0.44
     élas
    0.43
    Activations Density 1.403%

    No Known Activations