© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11872
    Prev
    Next
    INDEX
    Explanations

    words/phrases associated with professional organizations and publications, particularly those relating to history, science, and mathematics, and potentially those based in America

    oai_token-act-pair · gemini-2.0-flash

    professional and academic contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     كومونز
    -0.94
     صوتيه
    -0.85
    IntoConstraints
    -0.85
     committee
    -0.84
     gyhoeddwyd
    -0.81
    évaluateur
    -0.80
    Committee
    -0.78
     rhestr
    -0.78
    Council
    -0.78
     Committee
    -0.78
    POSITIVE LOGITS
     commit
    0.69
     ass
    0.65
    Ass
    0.59
     committed
    0.56
     Ass
    0.56
    Commit
    0.52
    commit
    0.52
     commits
    0.51
     Commit
    0.50
     COMMIT
    0.48
    Activations Density 2.063%

    No Known Activations