© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11888
    Prev
    Next
    INDEX
    Explanations

    the word "address" as a verb.

    oai_token-act-pair · gemini-2.0-flash

    address

    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
    +#+#
    -0.87
    CloseOperation
    -0.82
    تقاوى
    -0.75
    ChildScrollView
    -0.75
     Савезне
    -0.75
    InvalidProtocol
    -0.74
     addressed
    -0.73
     addressing
    -0.69
     onBind
    -0.69
    клопе
    -0.69
    POSITIVE LOGITS
    OIS
    0.59
    ⓘ
    0.56
     fallu
    0.54
    FPGA
    0.49
    masing
    0.49
    あえず
    0.49
    abetes
    0.49
    naio
    0.49
     tato
    0.48
     actionMode
    0.47
    Activations Density 0.561%

    No Known Activations