© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 3610
    Prev
    Next
    INDEX
    Explanations

    math papers, looking for notation, theorem mentions, and morphism mappings.

    oai_token-act-pair · gemini-2.0-flash

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    twimg
    -0.69
    aarrggbb
    -0.66
    photobucket
    -0.66
    verwijspagina
    -0.63
     surla
    -0.62
     <>",
    -0.62
    HIGHLIGHTS
    -0.61
    atrième
    -0.61
    bootstrapcdn
    -0.60
    CreateMap
    -0.60
    POSITIVE LOGITS
    ScopeManager
    0.49
    AutoScaleMode
    0.46
     custard
    0.45
    Linki
    0.43
    യി
    0.42
    Người
    0.42
    GUILayout
    0.42
    графия
    0.42
     nargin
    0.41
    œuvre
    0.41
    Activations Density 1.304%

    No Known Activations