© 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. 2652
    Prev
    Next
    INDEX
    Explanations

    sentences that contain the word "take" or its variations

    oai_token-act-pair · gemini-2.0-flash

    take

    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
     kasarigan
    -0.78
     AssemblyCulture
    -0.68
     незавершена
    -0.67
    FunctionFlags
    -0.65
    featureID
    -0.62
    exitRule
    -0.62
     nahilalakip
    -0.61
    AutoresizingMask
    -0.61
    adpleegd
    -0.60
    ANTLR
    -0.60
    POSITIVE LOGITS
    yad
    0.56
    asInstanceOf
    0.56
    sgn
    0.55
     nothing
    0.49
    tesi
    0.48
     lanjut
    0.47
    URANCE
    0.46
     segu
    0.46
    greifen
    0.46
    cijos
    0.44
    Activations Density 0.413%

    No Known Activations