© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9593
    Prev
    Next
    INDEX
    Explanations

    scientific or medical studies that involve polysaccharides or pemphigus or that have the letter P as an initial

    oai_token-act-pair · gemini-2.0-flash

    studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    if
    -1.07
    r
    -0.97
    p
    -0.94
    w
    -0.93
    ,
    -0.93
    an
    -0.93
    in
    -0.93
    .
    -0.91
    0
    -0.89
    for
    -0.89
    POSITIVE LOGITS
     Efq
    1.73
     itſelf
    1.69
     myſelf
    1.66
    ^(@)
    1.55
     raiſ
    1.53
    ſelves
    1.50
    leſs
    1.48
    BibitemShut
    1.47
     themſelves
    1.47
    olesale
    1.47
    Activations Density 6.482%

    No Known Activations