© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9606
    Prev
    Next
    INDEX
    Explanations

    the words "can," "will," and "should," or words paired with them

    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_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    -0.60
     Can
    -0.59
     can
    -0.59
    can
    -0.54
    PerformLayout
    -0.48
    ustre
    -0.47
     CAN
    -0.46
    Protocol
    -0.45
    CAN
    -0.44
     completion
    -0.43
    POSITIVE LOGITS
     contextLoads
    0.88
     BorderRadius
    0.79
     Baillargeon
    0.68
     betweenstory
    0.67
     saites
    0.67
    endphp
    0.66
    tdessen
    0.65
     InputDecoration
    0.64
    ViewImports
    0.64
     Huerta
    0.63
    Activations Density 3.784%

    No Known Activations