© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 3678
    Prev
    Next
    INDEX
    Explanations

    text about printing or fonts

    oai_token-act-pair · gemini-2.0-flash

    software commands

    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
    '])->
    -0.84
    "]);
    
    -0.77
    ]));
    
    -0.75
    '}>
    -0.73
    '));
    
    -0.73
    ')));
    -0.72
    '])){
    
    -0.72
    ']));
    -0.71
    twimg
    -0.69
    ."]
    -0.66
    POSITIVE LOGITS
    AddTagHelper
    0.70
    ANTLR
    0.60
    DMETHOD
    0.59
    InteropServices
    0.58
    QtGui
    0.54
    onAttach
    0.53
    DialogInterface
    0.52
    ClientSize
    0.49
    XmlType
    0.49
    ReusableCell
    0.48
    Activations Density 3.485%

    No Known Activations