© 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. 0-GEMMASCOPE-TRANSCODER-16K
    4. 8361
    Prev
    Next
    INDEX
    Explanations

    the word "wise."

    oai_token-act-pair · gemini-2.0-flash

    wise

    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
    ".
    
    -1.18
    .)}
    -1.05
    "});
    -1.04
    ."));
    -1.03
    "},
    
    -1.03
    "],
    
    -1.01
    ).}
    -1.01
    /}.
    -0.97
    '},
    
    -0.96
    )");
    
    -0.96
    POSITIVE LOGITS
    _
    0.61
     petto
    0.57
    y
    0.54
    
    0.54
    .
    0.51
     anisotropy
    0.50
     cavitation
    0.50
    bukkit
    0.50
     conformal
    0.48
     exud
    0.48
    Activations Density 1.876%

    No Known Activations