© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11682
    Prev
    Next
    INDEX
    Explanations

    text related to numbers, percentages, and financial amounts

    oai_token-act-pair · gemini-2.0-flash

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    expandindo
    -0.84
     Theſe
    -0.81
     وتسجيلات
    -0.78
    offsetof
    -0.77
    principalColumn
    -0.75
     gyhoeddwyd
    -0.74
    发表于
    -0.73
    AccessorTable
    -0.73
    nEnter
    -0.73
    writeFieldEnd
    -0.72
    POSITIVE LOGITS
     represent
    0.60
     representative
    0.54
     repre
    0.52
    Represent
    0.52
     represents
    0.52
     REPRESENT
    0.51
     representing
    0.50
    representative
    0.49
     for
    0.49
     Represent
    0.48
    Activations Density 1.699%

    No Known Activations