© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7713
    Prev
    Next
    INDEX
    Explanations

    the phrase "have" preceded by modal verbs, especially "might," "would," or "could".

    oai_token-act-pair · gemini-2.0-flash

    have

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    unately
    -0.66
     Meksiku
    -0.62
     pinulongan
    -0.58
     mắn
    -0.56
    ējās
    -0.56
    stateMutability
    -0.56
     oração
    -0.54
     fortn
    -0.52
     katanya
    -0.52
     geçen
    -0.52
    POSITIVE LOGITS
     gotten
    0.68
     belonged
    0.64
     been
    0.63
    <bos>
    0.60
     seemed
    0.57
     believed
    0.56
     corresponded
    0.55
    íncia
    0.55
     enjoyed
    0.54
     lacked
    0.54
    Activations Density 1.282%

    No Known Activations