© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14311
    Prev
    Next
    INDEX
    Explanations

    words that appear to be from a language other than English used within English text

    oai_token-act-pair · gemini-2.0-flash

    Malay internet content

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     محفوظة
    -0.65
     kasarigan
    -0.59
     initComponents
    -0.58
    enumi
    -0.57
    QMetaType
    -0.55
     saites
    -0.54
    enumii
    -0.54
    NameInMap
    -0.52
    reactstrap
    -0.52
     HttpNotFound
    -0.52
    POSITIVE LOGITS
     HRS
    0.54
     pleaſure
    0.48
    Flashback
    0.47
    ampingi
    0.45
    URBANA
    0.45
    destroyAll
    0.43
    GroupBy
    0.43
    annya
    0.43
    tonsoft
    0.43
    ANGAN
    0.43
    Activations Density 0.601%

    No Known Activations