© 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. 3271
    Prev
    Next
    INDEX
    Explanations

    words and phrases in other languages (Cyrillic, German, Portuguese) with particular emphasis on sentence structure and punctuation

    oai_token-act-pair · 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
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -3.11
     itſelf
    -3.06
     Efq
    -2.77
     pleaſure
    -2.70
    <bos>
    -2.64
    ſelf
    -2.61
     Monfieur
    -2.59
     raiſ
    -2.48
     Jefus
    -2.48
     themſelves
    -2.47
    POSITIVE LOGITS
     
    1.30
    ,
    1.29
    .
    1.28
     (
    1.24
    <eos>
    1.24
    :
    1.11
     “
    1.08
    ↵
    1.05
     in
    1.05
     "
    1.04
    Activations Density 0.268%

    No Known Activations