© 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-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10770
    Prev
    Next
    INDEX
    Explanations

    words related to conservation, prevention, and treatment, especially in the context of health and environmental issues

    oai_token-act-pair · gemini-2.0-flash

    conservation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     Theſe
    -1.00
    PerformLayout
    -0.97
     myſelf
    -0.96
     houſe
    -0.96
    expandindo
    -0.92
     Efq
    -0.90
     auffi
    -0.87
     themſelves
    -0.87
     purpoſe
    -0.86
     snippetHide
    -0.84
    POSITIVE LOGITS
    /
    0.47
     /
    0.43
     b
    0.42
    ist
    0.41
     works
    0.39
     issues
    0.38
    働
    0.38
     t
    0.38
    mois
    0.38
    to
    0.37
    Activations Density 1.556%

    No Known Activations