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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15048
    Prev
    Next
    INDEX
    Explanations

    code-related terms such as languages and error messages.

    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_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
    <bos>
    -2.80
     Paglinawan
    -1.66
     betweenstory
    -1.64
    WithIOException
    -1.63
    Rüyada
    -1.62
     resourceCulture
    -1.54
     Roskov
    -1.48
     propOrder
    -1.44
     Савезне
    -1.41
     Мексичка
    -1.40
    POSITIVE LOGITS
     
    1.12
    .
    1.05
    ,
    0.90
    </i>
    0.87
    </em>
    0.86
     .
    0.85
     (
    0.82
      
    0.79
    <b>
    0.77
    <strong>
    0.76
    Activations Density 6.276%

    No Known Activations