© 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. 14773
    Prev
    Next
    INDEX
    Explanations

    words associated with scientific experiments and cancer

    oai_token-act-pair · gemini-2.0-flash

    scientific studies

    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
    出版年
    -0.65
    KommentareTeilen
    -0.61
     continúas
    -0.59
    __;
    -0.59
     Analyzed
    -0.59
     analysed
    -0.57
     accurately
    -0.56
     exatamente
    -0.56
     exactly
    -0.56
     analyzed
    -0.56
    POSITIVE LOGITS
     propOrder
    0.56
    providedIn
    0.56
    nimo
    0.52
    icoot
    0.48
    IZON
    0.48
    èdia
    0.47
     Pingback
    0.46
    mended
    0.46
    SARA
    0.45
    izr
    0.45
    Activations Density 12.004%

    No Known Activations