© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 9489
    Prev
    Next
    INDEX
    Explanations

    words that indicate a degree of excess

    oai_token-act-pair · gemini-2.0-flash

    excessive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ViewFeatures
    -0.64
    věř
    -0.52
    excess
    -0.52
    beginTransaction
    -0.50
    Excess
    -0.49
     excess
    -0.49
     ře
    -0.48
    gründet
    -0.47
    CloseOperation
    -0.47
     IndexPath
    -0.47
    POSITIVE LOGITS
     ſy
    0.75
     Majefty
    0.69
     onBind
    0.69
     Monfieur
    0.69
     reaſon
    0.67
     Houſe
    0.66
     Allociné
    0.66
     theſe
    0.66
     ſche
    0.65
     Theſe
    0.65
    Activations Density 3.356%

    No Known Activations