© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 9694
    Prev
    Next
    INDEX
    Explanations

    the word "board", especially when in the context of wiring or printed circuit boards

    oai_token-act-pair · gemini-2.0-flash

    board

    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
    Negative Logits
     board
    -3.06
    board
    -3.06
    Board
    -2.61
     Board
    -2.59
    BOARD
    -2.58
     BOARD
    -2.48
    boards
    -2.39
     boards
    -2.30
     Boards
    -2.05
    Boards
    -1.83
    POSITIVE LOGITS
    NameInMap
    0.66
    #+#
    0.65
    __':
    0.64
    __":
    0.56
    PathVariable
    0.52
     neuve
    0.51
    !*\
    0.50
     EconPapers
    0.50
     doInBackground
    0.49
     gray
    0.48
    Activations Density 0.415%

    No Known Activations