© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 560
    Prev
    Next
    INDEX
    Explanations

    words associated with people, especially those who do things.

    oai_token-act-pair · gemini-2.0-flash

    people

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    AddTagHelper
    -0.87
     autorytatywna
    -0.83
    DotNetBar
    -0.82
     समीक्षक
    -0.80
    发表于
    -0.74
     ligiloj
    -0.71
     createSlice
    -0.71
    createCanvas
    -0.69
     '\\;'
    -0.69
    awtextra
    -0.68
    POSITIVE LOGITS
    [--
    0.62
    '
    0.59
    ’
    0.54
    ̷
    0.45
    '
    
    0.45
     $^{\
    0.43
    
    0.43
     consign
    0.41
     '
    
    0.41
    \'
    0.40
    Activations Density 15.203%

    No Known Activations