© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5940
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with biochemistry and molecular biology experiments, especially those involving proteins, cells and antibodies.

    oai_token-act-pair · gemini-2.0-flash

    protein lab experiment

    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
     MonoBehaviour
    -0.55
    reportWebVitals
    -0.54
     cultures
    -0.51
    IsInitialized
    -0.48
     Sign
    -0.48
     nein
    -0.48
     Cultures
    -0.47
     snippetHide
    -0.46
    kult
    -0.46
    layouts
    -0.45
    POSITIVE LOGITS
     חיצוניים
    0.65
    abetes
    0.64
    eseed
    0.63
     Белару
    0.59
    gemeester
    0.56
    roek
    0.54
    ptonshire
    0.52
    тарь
    0.51
    topatho
    0.50
    rostis
    0.50
    Activations Density 4.022%

    No Known Activations