© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5628
    Prev
    Next
    INDEX
    Explanations

    the word "won" and "winners"

    oai_token-act-pair · gemini-2.0-flash

    won

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     won
    -2.23
    <bos>
    -1.83
    Won
    -1.80
    won
    -1.76
     WON
    -1.74
     Won
    -1.70
    WON
    -1.44
     winning
    -1.34
     wins
    -1.30
     wont
    -1.17
    POSITIVE LOGITS
    wieś
    0.59
    sidemargin
    0.51
    LikeLike
    0.49
    UAGES
    0.47
     continuant
    0.47
     щодо
    0.47
     DialogInterface
    0.47
    ubber
    0.46
     Fern
    0.44
    mandu
    0.44
    Activations Density 0.182%

    No Known Activations