© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15067
    Prev
    Next
    INDEX
    Explanations

    the word "th" in texts including scientific and political subjects

    oai_token-act-pair · gemini-2.0-flash

    Th

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    utsu
    -0.47
    Scanning
    -0.47
     Knight
    -0.46
    iformes
    -0.46
     المهم
    -0.45
    estat
    -0.45
     Kevin
    -0.45
    MediaStore
    -0.45
     vanta
    -0.44
     estat
    -0.44
    POSITIVE LOGITS
    TypedDataSet
    0.69
    elemField
    0.69
     الرياضيه
    0.66
    IGraphics
    0.65
     kaarangay
    0.65
    vânt
    0.62
     femininas
    0.61
     Monfieur
    0.60
    contentLoaded
    0.60
    ſelves
    0.59
    Activations Density 0.396%

    No Known Activations