© 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. 15500
    Prev
    Next
    INDEX
    Explanations

    the word "conversation" and other words related to discussing, debating, or understanding

    oai_token-act-pair · gemini-2.0-flash

    conversation

    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
    ')],
    -0.61
     cy
    -0.57
    `}
    -0.56
     
    -0.55
    cy
    -0.55
    cur
    -0.54
     Sé
    -0.54
     ‘
    -0.53
     QtWidgets
    -0.53
     the
    -0.52
    POSITIVE LOGITS
     ainfi
    1.02
    ergies
    0.94
    ínű
    0.93
     auffi
    0.91
     avoient
    0.90
     plufieurs
    0.90
     abstrait
    0.88
     vermelhas
    0.86
     Daß
    0.86
     chrétien
    0.85
    Activations Density 1.944%

    No Known Activations