© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13199
    Prev
    Next
    INDEX
    Explanations

    information about scientific research, particularly related to structural biology and virology, including PDB entries, virus names, and research-related abbreviations.

    oai_token-act-pair · gemini-2.0-flash

    PDB entries

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    bootstrapcdn
    -0.85
     nakalista
    -0.79
    __*/
    -0.77
    AddHtmlAttribute
    -0.72
    XmlAccessorType
    -0.71
    ValueStyle
    -0.70
    ViewInit
    -0.69
    Manbalar
    -0.69
    Referencies
    -0.68
     kasarigan
    -0.68
    POSITIVE LOGITS
    q
    0.66
    w
    0.58
    h
    0.58
    j
    0.57
    r
    0.56
    m
    0.56
    v
    0.56
    p
    0.56
    k
    0.56
    n
    0.53
    Activations Density 3.597%

    No Known Activations