© 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. 5186
    Prev
    Next
    INDEX
    Explanations

    this neuron appears to be matching words in code snippets or technical documents, with some association to personal anecdotes or scenarios

    oai_token-act-pair · gemini-2.0-flash

    Code/Technical text

    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
    mybatisplus
    -1.04
     surla
    -0.94
    gameserver
    -0.85
    Geplaatst
    -0.85
    UnsafeEnabled
    -0.82
    Tikang
    -0.82
     Endoc
    -0.81
    ագրություններ
    -0.80
     AspNetCore
    -0.79
    ThroughAttribute
    -0.79
    POSITIVE LOGITS
    $}}
    0.56
    %")
    0.53
    ^*)
    0.52
    ]")
    0.47
    })();
    
    0.47
    "];
    
    0.46
     e
    0.46
    "));
    
    0.45
    ]";
    0.45
    '));
    
    0.44
    Activations Density 8.368%

    No Known Activations