© 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. 9442
    Prev
    Next
    INDEX
    Explanations

    code-related tokens such as programming keywords, variables, and debugging terms

    oai_token-act-pair · gemini-2.0-flash

    code and system messages

    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
    Not in Any Lists

    No Comments

    Negative Logits
    "):
    
    -0.74
    "},
    
    -0.73
    "))
    
    -0.60
    >";
    
    -0.59
    )");
    
    -0.58
    ":
    
    -0.58
    ="">
    
    -0.58
    ")));
    
    -0.56
    )}_
    -0.56
    ]:
    
    -0.55
    POSITIVE LOGITS
    MigrationBuilder
    0.84
    oredCriteria
    0.76
     indisponible
    0.75
    DockStyle
    0.74
    verwijspagina
    0.72
     '\\;'
    0.72
    <bos>
    0.71
    mybatisplus
    0.70
     ProtoMessage
    0.69
    sizeCache
    0.68
    Activations Density 3.170%

    No Known Activations