© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11387
    Prev
    Next
    INDEX
    Explanations

    words related to programming syntax and file nomenclature

    oai_token-act-pair · gemini-2.0-flash

    ule

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     senti
    -0.47
    HARR
    -0.44
    Coded
    -0.42
    singular
    -0.42
    essions
    -0.40
    bital
    -0.40
     puțin
    -0.39
    ストア
    -0.39
     zucca
    -0.39
     Sci
    -0.38
    POSITIVE LOGITS
     مشين
    1.11
    +#+#
    0.82
     AssemblyCulture
    0.81
     EconPapers
    0.79
    InjectAttribute
    0.79
    rostis
    0.79
    脚注の使い方
    0.78
    __":
    0.75
     <>",
    0.75
    UnsafeEnabled
    0.75
    Activations Density 3.182%

    No Known Activations