© 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. 1671
    Prev
    Next
    INDEX
    Explanations

    the word "can" and words that immediately come before or after it

    oai_token-act-pair · gemini-2.0-flash

    can

    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
     can
    -1.63
    can
    -1.40
    Can
    -1.37
     Can
    -1.33
     CAN
    -1.03
    CAN
    -0.96
     dapat
    -0.87
    可以
    -0.78
     could
    -0.75
     kann
    -0.75
    POSITIVE LOGITS
    makeConstraints
    0.90
     CreateTagHelper
    0.76
    setLayoutManager
    0.71
    TagMode
    0.71
    ReusableCell
    0.67
    principalColumn
    0.66
    ANTLR
    0.65
    WaitGroup
    0.63
    andidates
    0.59
    AccessorTable
    0.59
    Activations Density 2.765%

    No Known Activations