© 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. 2747
    Prev
    Next
    INDEX
    Explanations

    words and phrases describing scientific research processes and results

    oai_token-act-pair · gemini-2.0-flash

    Scientific conditions/processes

    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
     myſelf
    -0.75
     Efq
    -0.68
     Jefus
    -0.61
     himſelf
    -0.60
    ſelf
    -0.58
     houſe
    -0.57
     ―――――
    -0.57
     ſeveral
    -0.57
     whoſe
    -0.56
     Chriftian
    -0.56
    POSITIVE LOGITS
     Conditions
    0.82
     Behaviors
    0.78
     Issues
    0.75
     Processes
    0.75
     Measures
    0.75
     Factors
    0.74
     Connections
    0.74
     Control
    0.74
     Behavior
    0.74
     Properties
    0.73
    Activations Density 16.176%

    No Known Activations