© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7099
    Prev
    Next
    INDEX
    Explanations

    single-character variables in code, as well as some terms related to programming.

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    t
    -1.05
    d
    -1.04
    n
    -0.91
    s
    -0.87
    r
    -0.78
    g
    -0.77
    ness
    -0.71
    p
    -0.67
    l
    -0.66
    m
    -0.65
    POSITIVE LOGITS
    原始内容存档于
    0.67
     Roskov
    0.66
    AddHtmlAttribute
    0.60
    ьаж
    0.59
    SharedDtor
    0.58
    invokeLater
    0.56
    archiviato
    0.54
    RegressionTest
    0.53
     [*]
    0.52
    참고
    0.52
    Activations Density 17.843%

    No Known Activations