© 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
    2. Gemma-2-2B
    3. 6-GEMMASCOPE-TRANSCODER-16K
    4. 14152
    Prev
    Next
    INDEX
    Explanations

    snippets of code, particularly java

    oai_token-act-pair · gemini-2.0-flash

    Computer programming/data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    ")));
    
    -0.79
    )";
    
    -0.79
    >");
    
    -0.76
    })));
    -0.76
    >";
    
    -0.71
    ]--;
    -0.70
    ")){
    
    -0.70
    "],
    
    -0.70
    ]";
    -0.69
    "];
    
    -0.69
    POSITIVE LOGITS
    <bos>
    0.68
    WSGI
    0.52
    oa̍t
    0.49
    StructEnd
    0.48
     lateinit
    0.46
     propTypes
    0.46
     AppColors
    0.45
    ingeki
    0.45
    CppMethod
    0.45
    WithIOException
    0.44
    Activations Density 3.891%

    No Known Activations