© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 5180
    Prev
    Next
    INDEX
    Explanations

    file paths and related computer administrative terms

    oai_token-act-pair · gemini-2.0-flash

    file paths

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    withIdentifier
    -0.55
    Quark
    -0.52
     pungkasnya
    -0.52
    etna
    -0.50
    localScale
    -0.48
    fxml
    -0.48
    
    -0.48
    Unmarshal
    -0.47
     Quark
    -0.46
    mius
    -0.45
    POSITIVE LOGITS
     propOrder
    0.75
     autorytatywna
    0.69
    Autoritní
    0.67
     pinulongan
    0.66
    WithIOException
    0.63
    Carriera
    0.60
    RTDA
    0.59
    Enllaces
    0.59
    Personensuche
    0.58
     lenker
    0.58
    Activations Density 4.884%

    No Known Activations