© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12966
    Prev
    Next
    INDEX
    Explanations

    the start of C# "using" statements, particularly those related to the System namespace or the letters "cs"

    oai_token-act-pair · gemini-2.0-flash

    System

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -0.70
     préc
    -0.66
     Theſe
    -0.65
    bootstrapcdn
    -0.64
     getDefault
    -0.62
    wikimedia
    -0.62
     sérieux
    -0.62
     succès
    -0.60
     amitié
    -0.60
     Ressource
    -0.60
    POSITIVE LOGITS
    sizeCache
    0.73
    ExecuteReader
    0.66
     pageContext
    0.60
    BlockPos
    0.60
    writeFieldEnd
    0.60
    SocketAddress
    0.59
    onAttach
    0.59
    قایناق‌لار
    0.59
     doInBackground
    0.57
    tableFuture
    0.56
    Activations Density 0.196%

    No Known Activations