© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 13509
    Prev
    Next
    INDEX
    Explanations

    the end of code blocks, especially in javascript

    oai_token-act-pair · gemini-2.0-flash

    };

    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
    Negative Logits
     Efq
    -2.45
    ^(@)
    -2.36
     ―――――
    -2.22
     myſelf
    -2.17
     Majefty
    -2.17
    .";
    
    -2.17
     $_"
    -2.16
     Houſe
    -2.11
     Jefus
    -2.09
     ་་
    -2.09
    POSITIVE LOGITS
    <bos>
    2.52
    ↵
    1.83
    ↵↵
    1.60
    '
    1.50
     
    1.39
      
    1.38
    (
    1.37
    1
    1.30
    .
    1.27
        
    1.26
    Activations Density 0.878%

    No Known Activations