© 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
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3260
    Prev
    Next
    INDEX
    Explanations

    the symbols used in coding, such as 'if', parentheses, brackets, and equals signs

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     الوطنيه
    -0.60
     nakalista
    -0.59
    +#+
    -0.56
     RoutedEventArgs
    -0.56
    Carriera
    -0.55
    帖最后由
    -0.54
    panorama
    -0.54
     initComponents
    -0.54
     opérateurs
    -0.54
     traités
    -0.53
    POSITIVE LOGITS
     (),
    0.45
    })));
    0.44
     「
    0.44
     Infatti
    0.44
     (/
    0.43
    ContentAsync
    0.42
     （
    0.42
     М
    0.42
     "");
    0.41
     Monfieur
    0.41
    Activations Density 8.569%

    No Known Activations