© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10127
    Prev
    Next
    INDEX
    Explanations

    words that are in a language other than English, likely Malay

    oai_token-act-pair · gemini-2.0-flash

    code and data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Normdatei
    -1.01
     Efq
    -0.98
     houſe
    -0.93
     Monfieur
    -0.93
     ſeveral
    -0.93
     pleaſure
    -0.91
     Houſe
    -0.91
     NSCoder
    -0.90
     myſelf
    -0.88
     purpoſe
    -0.88
    POSITIVE LOGITS
     şi
    0.51
     zi
    0.50
     organiser
    0.50
     apologise
    0.49
     organise
    0.49
     utilise
    0.47
    ans
    0.46
     emphasise
    0.46
     organisers
    0.46
     д
    0.46
    Activations Density 0.035%

    No Known Activations