© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2667
    Prev
    Next
    INDEX
    Explanations

    indented lines of code

    oai_token-act-pair · gemini-2.0-flash

    specific programming or data-related terminology

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     disambiguazione
    -0.86
    SharedCtor
    -0.69
    WireFormatLite
    -0.66
    RenderAtEndOf
    -0.64
    gdx
    -0.63
    GOTREF
    -0.63
     متعلقه
    -0.62
    省市镇
    -0.61
    AccessorTable
    -0.60
    Tembelea
    -0.60
    POSITIVE LOGITS
    SequentialGroup
    0.60
    contentLoaded
    0.52
     Signalez
    0.46
    fromnode
    0.45
     Reichs
    0.45
    AddHtmlAttribute
    0.45
    TypedDataSet
    0.44
    modelBuilder
    0.40
     Geben
    0.39
     fence
    0.38
    Activations Density 1.323%

    No Known Activations