© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 9692
    Prev
    Next
    INDEX
    Explanations

    the word "could"

    oai_token-act-pair · gemini-2.0-flash

    could

    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
    Negative Logits
     could
    -1.98
    could
    -1.90
    Could
    -1.66
     Could
    -1.64
     COULD
    -1.44
     poderia
    -1.19
     könnten
    -1.05
     könnte
    -1.02
     pourrait
    -1.00
     podría
    -0.98
    POSITIVE LOGITS
    tvguidetime
    0.62
    '])->
    0.54
    "]];
    0.53
    jsdelivr
    0.53
    "]
    0.53
    ))->
    0.53
    UrlEncoded
    0.52
    бав
    0.52
    ]]
    0.51
    </strong>
    0.49
    Activations Density 0.648%

    No Known Activations