© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 9594
    Prev
    Next
    INDEX
    Explanations

    what appear to be suffixes and/or improperly encoded characters

    oai_token-act-pair · gemini-2.0-flash

    Code/technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    g
    -1.15
    ga
    -0.94
    gt
    -0.93
    gs
    -0.91
    ging
    -0.89
    gi
    -0.84
    gg
    -0.82
    gar
    -0.81
    gad
    -0.80
    gn
    -0.78
    POSITIVE LOGITS
    Viki
    0.60
    ollectionView
    0.59
     angiogenesis
    0.57
    createCanvas
    0.56
     linkovi
    0.56
     getRule
    0.55
    MigrationBuilder
    0.54
    InputTagHelper
    0.54
    testng
    0.54
    XmlAccessType
    0.52
    Activations Density 1.972%

    No Known Activations