© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 12177
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially C++ and Java it seems

    oai_token-act-pair · gemini-2.0-flash

    code involving sizes

    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
     AssemblyTitle
    -0.58
    ministerium
    -0.50
     Bibliothèque
    -0.50
    IBarButtonItem
    -0.48
    withIdentifier
    -0.47
    ImageContext
    -0.46
    styleUrls
    -0.46
     $+
    -0.46
    TypedDataSet
    -0.45
    routeProvider
    -0.45
    POSITIVE LOGITS
    -
    1.11
    ]--;
    0.95
    )++;
    0.92
    )];
    
    0.92
    ,:);
    0.91
    --)
    
    0.85
    )]);
    0.85
    ()]);
    0.84
    [];
    
    0.83
    ]';
    0.82
    Activations Density 11.087%

    No Known Activations