© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10551
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to archaeology and unearthing artifacts.

    oai_token-act-pair · gemini-2.0-flash

    excavating

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    inetto
    -0.51
    loy
    -0.48
     ellen
    -0.45
    וד
    -0.43
    jel
    -0.40
    hemi
    -0.40
    llo
    -0.40
     moc
    -0.39
    inum
    -0.39
    try
    -0.38
    POSITIVE LOGITS
     مشين
    0.94
    
    0.88
     ModelExpression
    0.83
    uxxxx
    0.81
     يتيمه
    0.80
    WithIOException
    0.80
     AssemblyCulture
    0.79
    terase
    0.79
    IsMutable
    0.78
     <<<<<<<<<<<<<<
    0.77
    Activations Density 0.428%

    No Known Activations