© 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. 2181
    Prev
    Next
    INDEX
    Explanations

    code snippets related to including javascript libraries in HTML

    oai_token-act-pair · gemini-2.0-flash

    Javascript, HTML code

    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
     &___
    -1.08
    parsedMessage
    -0.96
     Мексичка
    -0.93
    IUrlHelper
    -0.92
    WithIOException
    -0.91
    
    -0.90
     мәкал
    -0.90
    +#+
    -0.89
    Autoritní
    -0.87
    Geplaatst
    -0.86
    POSITIVE LOGITS
     Full
    0.45
     mo
    0.43
    Full
    0.43
     light
    0.40
     sar
    0.39
     AM
    0.39
    sar
    0.39
     quedado
    0.39
    dij
    0.38
    jol
    0.38
    Activations Density 1.523%

    No Known Activations