© 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. 10600
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a person's history or roles

    oai_token-act-pair · gemini-2.0-flash

    was

    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
    CodedInputStream
    -0.58
    DockStyle
    -0.57
     supérieures
    -0.52
    PROV
    -0.51
    didSet
    -0.51
     kasarigan
    -0.50
     supérieurs
    -0.50
    ConstraintMaker
    -0.50
    yonel
    -0.49
    getColumnIndex
    -0.48
    POSITIVE LOGITS
     one
    0.65
     among
    0.59
    ằ
    0.57
     AppModule
    0.56
     appalled
    0.54
     nominated
    0.52
    %=
    0.51
     born
    0.51
     married
    0.50
     ReactDOM
    0.49
    Activations Density 0.597%

    No Known Activations