© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 16227
    Prev
    Next
    INDEX
    Explanations

    the word "would"

    oai_token-act-pair · gemini-2.0-flash

    would

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     would
    -0.86
    would
    -0.76
     Would
    -0.72
    Would
    -0.71
     wouldn
    -0.59
     WOULD
    -0.59
    Wouldn
    -0.56
    wouldn
    -0.55
    D
    -0.51
     avrebbe
    -0.50
    POSITIVE LOGITS
     مرئيه
    0.78
    IBAction
    0.72
    InjectAttribute
    0.71
    ellites
    0.71
    ")));
    0.70
    Архівовано
    0.70
    fillType
    0.70
     saites
    0.68
    NameInMap
    0.68
     يتيمه
    0.66
    Activations Density 0.484%

    No Known Activations