© 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. 15904
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming-related keywords such as "struct", "let", "array", "compile", and "script".

    oai_token-act-pair · gemini-2.0-flash

    arrays and lists

    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
    ArrayList
    -0.53
     matrix
    -0.52
     vector
    -0.51
     IList
    -0.51
    Vector
    -0.50
    isArray
    -0.49
    ARRAY
    -0.49
    FlatList
    -0.48
    ToArray
    -0.47
    ExecuteReader
    -0.47
    POSITIVE LOGITS
     ویکی‌پدیا
    0.81
     disambiguazione
    0.80
    !*\
    0.77
    DataAnnotations
    0.73
    ngdoc
    0.72
     otomatig
    0.72
     NSCoder
    0.71
    invokeLater
    0.68
    toThrow
    0.68
     Normdatei
    0.67
    Activations Density 47.646%

    No Known Activations