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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12501
    Prev
    Next
    INDEX
    Explanations

    configuration file data and code samples

    oai_token-act-pair · gemini-2.0-flash

    address

    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
    Not in Any Lists

    No Comments

    Negative Logits
    address
    -0.69
    Address
    -0.59
    ADDRESS
    -0.51
     address
    -0.51
    getAddress
    -0.49
    empi
    -0.45
     transfé
    -0.43
     Address
    -0.43
     consultez
    -0.42
    requireNonNull
    -0.42
    POSITIVE LOGITS
    tagHelperRunner
    0.90
     '\\;'
    0.85
    invokeLater
    0.77
     nahilalakip
    0.75
    SharedDtor
    0.75
     дописавши
    0.74
    MigrationBuilder
    0.73
    出版年
    0.73
    Collegamenti
    0.73
    NUMX
    0.71
    Activations Density 7.406%

    No Known Activations