© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2633
    Prev
    Next
    INDEX
    Explanations

    a mix of sentence-initial and capitalized words across a few languages

    oai_token-act-pair · gemini-2.0-flash

    Non-English code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    出版年
    -1.08
    SourceChecksum
    -1.02
     AssemblyCulture
    -1.01
    
    -0.91
     resourceCulture
    -0.90
     ExecuteAsync
    -0.84
     MainAxisSize
    -0.83
    UnusedPrivate
    -0.79
    ViewFeatures
    -0.78
    PerformLayout
    -0.77
    POSITIVE LOGITS
    água
    0.40
     general
    0.38
    setProduct
    0.36
    itsub
    0.36
     tł
    0.35
    GetName
    0.35
    hite
    0.35
    getEntity
    0.35
    general
    0.35
    maran
    0.35
    Activations Density 0.198%

    No Known Activations