© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11462
    Prev
    Next
    INDEX
    Explanations

    discussions of environmental regulations related to health

    oai_token-act-pair · gemini-2.0-flash

    Environmental pollution/regulation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     bParam
    -0.52
     mat
    -0.50
    rozco
    -0.48
     Dati
    -0.47
    odas
    -0.47
    oda
    -0.46
    AsUp
    -0.46
    shtml
    -0.45
    Amb
    -0.45
    oden
    -0.45
    POSITIVE LOGITS
     InputDecoration
    0.74
    __":
    0.73
    NewUrlParser
    0.69
    ReusableCell
    0.68
    脚注の使い方
    0.68
    awtextra
    0.67
    findpost
    0.66
    __":
    0.61
    __':
    0.61
     doInBackground
    0.60
    Activations Density 3.490%

    No Known Activations