© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2183
    Prev
    Next
    INDEX
    Explanations

    scientific and technical language, including measurements, codes, figures, and chemical compounds

    oai_token-act-pair · gemini-2.0-flash

    Scientific/technical labels

    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
    Not in Any Lists

    No Comments

    Negative Logits
    SourceChecksum
    -0.62
    Personensuche
    -0.54
    AndroidJUnit
    -0.50
    createTextNode
    -0.47
    sidemargin
    -0.46
    ][$
    -0.46
    XmlType
    -0.44
    DataPropertyName
    -0.43
    HasKey
    -0.43
    fır
    -0.43
    POSITIVE LOGITS
    bootstrapcdn
    0.57
     OnInit
    0.56
     nữa
    0.55
     IBOutlet
    0.55
    argo
    0.54
     Aguilera
    0.54
     Godt
    0.53
    cythe
    0.53
     odkazy
    0.52
    $}}
    0.52
    Activations Density 37.174%

    No Known Activations