© 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. 16118
    Prev
    Next
    INDEX
    Explanations

    C++ or similar code syntax, including keywords like private, public, virtual, class, and namespace elements

    oai_token-act-pair · gemini-2.0-flash

    private

    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
    WebServlet
    -0.50
    Odkazy
    -0.50
     Besøkt
    -0.48
    ResponseWriter
    -0.48
    Vidite
    -0.47
    Appearance
    -0.47
    MemoryWarning
    -0.45
    GetMapping
    -0.45
    Externí
    -0.45
     linkovi
    -0.45
    POSITIVE LOGITS
     bakgrund
    0.73
    behind
    0.72
    ]._
    0.69
     internos
    0.68
     internal
    0.66
     inside
    0.66
     internally
    0.66
     intérieure
    0.66
     Internal
    0.65
     interno
    0.65
    Activations Density 3.472%

    No Known Activations