© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14427
    Prev
    Next
    INDEX
    Explanations

    instances of the word "we"

    oai_token-act-pair · gemini-2.0-flash

    we

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     we
    -3.73
     мы
    -2.06
    we
    -1.81
    我們
    -1.65
    我们
    -1.58
     abbiamo
    -1.51
    我们可以
    -1.49
    私たちは
    -1.48
    我们就
    -1.48
    เรา
    -1.41
    POSITIVE LOGITS
    ↵↵
    0.80
    I
    0.73
    “
    0.72
    (
    0.71
    <strong>
    0.70
     They
    0.70
    "
    0.69
    ↵
    0.66
    ?
    0.65
    .
    0.65
    Activations Density 2.433%

    No Known Activations