© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12341
    Prev
    Next
    INDEX
    Explanations

    numbers appearing in the text

    oai_token-act-pair · gemini-2.0-flash

    numerical data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Monfieur
    -1.02
     becauſe
    -0.99
     pleaſure
    -0.97
     Theſe
    -0.95
     Anſ
    -0.93
     itſelf
    -0.93
     themſelves
    -0.91
     myſelf
    -0.91
     whoſe
    -0.89
     iſt
    -0.88
    POSITIVE LOGITS
     „
    0.64
    ё
    0.54
     wich
    0.53
    ём
    0.50
     Nowadays
    0.48
     «
    0.48
    pag
    0.48
    flav
    0.47
     B
    0.46
     apreci
    0.46
    Activations Density 3.458%

    No Known Activations