© 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. 271
    Prev
    Next
    INDEX
    Explanations

    mentions of websites, particularly on github and facebook, in a code-like context

    oai_token-act-pair · gemini-2.0-flash

    github or facebook

    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
     Biosciences
    -0.54
     EconPapers
    -0.48
     Commission
    -0.46
    لیت
    -0.45
    amssymb
    -0.44
    vensis
    -0.44
    λ
    -0.44
    وء
    -0.43
    ClCompile
    -0.43
     commission
    -0.43
    POSITIVE LOGITS
    .[/
    0.62
    — 
    0.59
    GeneratedValue
    0.49
     surla
    0.48
    ."</
    0.48
    .*/
    0.47
    "/></
    0.47
    tagHelperRunner
    0.47
    ,**
    0.46
    AttributeSet
    0.46
    Activations Density 2.799%

    No Known Activations