© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10335
    Prev
    Next
    INDEX
    Explanations

    the word "board" and words related to product packaging or company personnel

    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_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
     board
    -3.09
     Board
    -2.89
    Board
    -2.78
    board
    -2.78
     BOARD
    -2.61
     boards
    -2.56
    BOARD
    -2.38
     Boards
    -2.30
    boards
    -2.27
    Boards
    -2.16
    POSITIVE LOGITS
    WebElementEntity
    0.59
    
    0.57
    HEAST
    0.54
     Pelop
    0.53
     député
    0.53
    tisone
    0.53
     Pouch
    0.52
    ophobic
    0.52
    éfono
    0.52
     carats
    0.52
    Activations Density 4.101%

    No Known Activations