© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12906
    Prev
    Next
    INDEX
    Explanations

    the word "carry" and its variations

    oai_token-act-pair · gemini-2.0-flash

    carry

    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
     carry
    -2.63
     carried
    -2.50
     Carry
    -2.41
    carry
    -2.38
    Carry
    -2.36
     carries
    -2.28
     carrying
    -2.25
     CARRY
    -2.14
    carried
    -2.13
     Carrying
    -2.06
    POSITIVE LOGITS
    AccessorTable
    0.66
    SuccessListener
    0.57
    EFIAPI
    0.57
    HasMaxLength
    0.56
    setOnItem
    0.54
    ripto
    0.52
    ONIA
    0.50
     financières
    0.49
    onia
    0.49
    âts
    0.49
    Activations Density 0.380%

    No Known Activations