© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3810
    Prev
    Next
    INDEX
    Explanations

    language related to legal proceedings and government regulations

    oai_token-act-pair · gemini-2.0-flash

    licenses and regulations

    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
     resulted
    -1.12
     RESULT
    -0.98
     result
    -0.98
     Results
    -0.94
    result
    -0.93
     results
    -0.92
    results
    -0.91
     Result
    -0.90
    Results
    -0.88
     RESULTS
    -0.87
    POSITIVE LOGITS
    DockStyle
    0.60
    enderror
    0.54
     propOrder
    0.54
     dõi
    0.53
    SequentialGroup
    0.51
     author
    0.49
     estekak
    0.49
    ellery
    0.48
    փ
    0.48
    addCriterion
    0.47
    Activations Density 2.026%

    No Known Activations