© 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. 2534
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially C-like and Javascript-like languages, potentially involving numbers and class instantiations

    oai_token-act-pair · gemini-2.0-flash

    numbers

    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
    0
    -0.50
    1
    -0.47
     betweenstory
    -0.44
    idalgo
    -0.39
    stående
    -0.37
    QRect
    -0.36
     Gaspar
    -0.36
    ๆ
    -0.36
     للمعارف
    -0.36
     Newtonsoft
    -0.36
    POSITIVE LOGITS
    >())
    0.81
     =
    0.79
    ()))
    0.76
    ViewFeatures
    0.72
    (),
    0.71
    ();)
    0.71
    />";
    0.70
     >
    0.70
     |
    0.70
     nahilalakip
    0.68
    Activations Density 21.841%

    No Known Activations