© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14747
    Prev
    Next
    INDEX
    Explanations

    words in code and math snippets

    oai_token-act-pair · gemini-2.0-flash

    code/data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     FRO
    -0.72
    custo
    -0.68
     Destiny
    -0.65
     Legion
    -0.64
     pav
    -0.63
     Spro
    -0.63
     Lili
    -0.63
     Elgin
    -0.62
     Desai
    -0.62
     Esposito
    -0.62
    POSITIVE LOGITS
    ModelAdmin
    0.76
    :✨
    0.70
     Garrick
    0.70
    modelBuilder
    0.70
    tagHelperRunner
    0.69
    ArrowToggle
    0.68
     typelib
    0.67
    WebVitals
    0.66
    aarrggbb
    0.65
    SourceChecksum
    0.64
    Activations Density 5.689%

    No Known Activations