© 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
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13499
    Prev
    Next
    INDEX
    Explanations

    code snippets with keywords related to programming concepts such as objects, properties, types and methods

    oai_token-act-pair · gemini-2.0-flash

    programming in Portuguese

    np_max-act · gemini-2.0-flash

    section

    np_max-act-logits · gpt-5-mini
    Triggered by @chenshw0109
    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
    ArgsConstructor
    -1.13
     télécommande
    -1.08
     vectorielle
    -1.01
     paroisse
    -1.00
     متعلقه
    -1.00
     térmica
    -1.00
     larmes
    -1.00
     cardiaque
    -1.00
     algoritmo
    -0.99
     scolaires
    -0.98
    POSITIVE LOGITS
    <bos>
    0.92
     line
    0.89
     local
    0.85
     area
    0.80
    ↵↵
    0.80
     top
    0.79
     region
    0.72
     feature
    0.72
     specific
    0.72
     section
    0.72
    Activations Density 1.810%

    No Known Activations