© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 9805
    Prev
    Next
    INDEX
    Explanations

    C++ code syntax like namespaces, scopes, operators, and file extensions related elements

    oai_token-act-pair · gemini-2.0-flash

    ::

    np_max-act · gemini-2.0-flash

    ::

    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_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    
    -1.17
    GEBURTSDATUM
    -1.01
    abestanden
    -0.98
    AndEndTag
    -0.92
     snippetHide
    -0.90
     surla
    -0.84
    
    -0.82
     pinulongan
    -0.82
    Portale
    -0.77
    webElementGuid
    -0.76
    POSITIVE LOGITS
    <bos>
    0.73
    ազ
    0.48
    액
    0.48
     natuur
    0.48
    pannt
    0.47
     judiciales
    0.46
     linee
    0.46
     käyttö
    0.45
     poder
    0.44
     Públicas
    0.43
    Activations Density 1.486%

    No Known Activations