© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12230
    Prev
    Next
    INDEX
    Explanations

    the word "court" regardless of context, but is somewhat sensitive to other words nearby

    oai_token-act-pair · gemini-2.0-flash

    court

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     court
    -0.88
    court
    -0.62
    ViewFeatures
    -0.60
     akad
    -0.54
     hers
    -0.52
     courts
    -0.52
    ismet
    -0.51
    verz
    -0.51
    :+:
    -0.50
    qrst
    -0.50
    POSITIVE LOGITS
    yntaxException
    0.74
    complexType
    0.67
    sidemargin
    0.65
    ValueGeneration
    0.62
     protoimpl
    0.61
     betweenstory
    0.61
     noDo
    0.60
    ⓧ
    0.59
    setVerticalGroup
    0.59
     ISNI
    0.59
    Activations Density 0.723%

    No Known Activations