© 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. 3174
    Prev
    Next
    INDEX
    Explanations

    instances of something exceeding a limit, often with technical connotations

    oai_token-act-pair · gemini-2.0-flash

    exceed

    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
     "
    -0.64
    ↵↵
    -0.62
     '
    -0.59
     the
    -0.59
    cination
    -0.58
    '
    -0.56
    føring
    -0.54
    naire
    -0.52
    naires
    -0.51
     (
    -0.51
    POSITIVE LOGITS
     fermés
    0.96
     passés
    0.93
     feroit
    0.91
     Weeknd
    0.90
    ."));
    0.90
     pouvoit
    0.89
     ainfi
    0.87
     Tumors
    0.85
     avoient
    0.84
     Carcinoma
    0.84
    Activations Density 1.925%

    No Known Activations