© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7373
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to various technical fields such as genetics, advertising, and semiconductors

    oai_token-act-pair · gemini-2.0-flash

    digital documents

    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
    copg
    -0.60
    UIControlState
    -0.60
     Force
    -0.57
    tableFuture
    -0.56
    EntityFramework
    -0.55
    amarin
    -0.55
    Force
    -0.54
     Life
    -0.53
    Erfolge
    -0.53
    
    -0.52
    POSITIVE LOGITS
     Download
    0.83
     Printable
    0.80
     Screenshot
    0.79
     Spreadsheet
    0.78
     Video
    0.78
     Transcript
    0.77
     Texto
    0.77
     Updated
    0.77
     Template
    0.76
     Review
    0.73
    Activations Density 12.256%

    No Known Activations