Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-GEMMASCOPE-TRANSCODER-16K
    4. 12013
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially those using the words "List", "add", and parenthesis "(" or ")"

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    +};
    -0.56
    //});
    -0.55
    ORMAL
    -0.54
    ...');
    -0.54
     ');
    -0.50
    μφωνα
    -0.50
    []);
    -0.49
    drücken
    -0.49
     ?>
    
    -0.48
     []);
    -0.48
    POSITIVE LOGITS
    rungsseite
    0.60
     تضيفلها
    0.59
     OCS
    0.57
    yorsunuz
    0.57
     تانيه
    0.54
    ➟
    0.54
     diphtheria
    0.53
     оригіналу
    0.52
     yourselves
    0.52
     halves
    0.51
    Activations Density 0.393%

    No Known Activations