© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13636
    Prev
    Next
    INDEX
    Explanations

    code syntax, specifically for PHP, including HTML form submission data and database queries

    oai_token-act-pair · gemini-2.0-flash

    array

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    Tikang
    -0.82
    UnusedPrivate
    -0.75
    Rüyada
    -0.71
     Numerade
    -0.69
    DotNetBar
    -0.68
    tahui
    -0.66
    ///</
    -0.65
     udaler
    -0.62
    
    -0.59
     fewest
    -0.56
    POSITIVE LOGITS
     BoxFit
    0.49
     فريبيس
    0.49
    pēc
    0.48
    neté
    0.47
    quartered
    0.47
    ChildScrollView
    0.46
    RunAsync
    0.44
    翻
    0.44
    PyExc
    0.44
     edge
    0.43
    Activations Density 11.698%

    No Known Activations