© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10374
    Prev
    Next
    INDEX
    Explanations

    code-related terms, especially those in the Go language

    oai_token-act-pair · gemini-2.0-flash

    const

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    }{*}{}
    -0.48
    はじめに
    -0.45
    UMBIA
    -0.45
    र्फ
    -0.45
    ╮
    -0.44
    lidean
    -0.44
    вна
    -0.43
    Portale
    -0.43
    wige
    -0.42
    cuadro
    -0.42
    POSITIVE LOGITS
     AssemblyVersion
    0.96
     resourceCulture
    0.82
    NameInMap
    0.79
     ujednoznacz
    0.78
     BorderRadius
    0.76
     BoxFit
    0.75
     protoimpl
    0.72
    protoimpl
    0.70
    TemporalType
    0.70
     själva
    0.70
    Activations Density 6.749%

    No Known Activations