© 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. 2241
    Prev
    Next
    INDEX
    Explanations

    the words "array" and "number", when they are used in code

    oai_token-act-pair · gemini-2.0-flash

    array

    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
     array
    -2.38
     Array
    -2.31
    array
    -2.31
    Array
    -2.30
     arrays
    -1.97
     Arrays
    -1.76
     ARRAY
    -1.70
    ARRAY
    -1.66
    数组
    -1.55
    arrays
    -1.55
    POSITIVE LOGITS
     BorderSide
    0.68
     onCreateView
    0.66
    RegressionTest
    0.63
     CommandType
    0.62
     δὲ
    0.61
    TProtocol
    0.59
     Maak
    0.59
     ब्रेकडाउन
    0.59
    cleos
    0.59
    HandlerContext
    0.57
    Activations Density 2.029%

    No Known Activations