© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11866
    Prev
    Next
    INDEX
    Explanations

    the word "come".

    oai_token-act-pair · gemini-2.0-flash

    come

    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
     come
    -1.76
    Come
    -1.61
     Come
    -1.52
    come
    -1.48
     COME
    -1.36
    COME
    -1.26
     resourceCulture
    -0.83
    <bos>
    -0.76
    Билгалдахарш
    -0.73
     kasarigan
    -0.71
    POSITIVE LOGITS
     aprobó
    0.66
     zelve
    0.61
    weil
    0.59
     فهو
    0.57
     fiend
    0.56
     runways
    0.56
     שוליים
    0.56
     schuldig
    0.54
    tuce
    0.54
     bénéficiaire
    0.52
    Activations Density 0.151%

    No Known Activations