© 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. 9323
    Prev
    Next
    INDEX
    Explanations

    a mix of words in different languages, possibly related to code or configuration files

    oai_token-act-pair · gemini-2.0-flash

    Non-English language

    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
    VersionUID
    -0.63
    Datuak
    -0.59
     ivelany
    -0.58
    پیوند
    -0.57
    jfree
    -0.56
     depic
    -0.55
    antro
    -0.54
    ISupport
    -0.53
     للمعارف
    -0.52
    cupa
    -0.51
    POSITIVE LOGITS
    brainly
    0.63
    
    0.60
     externi
    0.59
     shivered
    0.46
    0.46
    KNOWN
    0.45
     Ud
    0.44
     Clínica
    0.44
    Reprints
    0.44
    withstanding
    0.43
    Activations Density 0.661%

    No Known Activations