© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2279
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with debate and argumentation

    oai_token-act-pair · gemini-2.0-flash

    pronouns referring to people

    np_token-act-pair-logits · gpt-4o-mini

    say "they"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    Their
    -0.99
     their
    -0.98
     Their
    -0.94
    their
    -0.83
     ihre
    -0.72
     ihren
    -0.72
     themselves
    -0.70
    themselves
    -0.70
     ihr
    -0.69
     ihrem
    -0.65
    POSITIVE LOGITS
     them
    2.31
     they
    2.31
    They
    1.99
     They
    1.96
    they
    1.95
    them
    1.81
     они
    1.69
     вони
    1.64
     mereka
    1.61
     них
    1.48
    Activations Density 12.235%

    No Known Activations