© 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. 9491
    Prev
    Next
    INDEX
    Explanations

    code or configuration file snippets

    oai_token-act-pair · gemini-2.0-flash

    special characters, code

    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
     становника
    -0.68
    DoubleQuotes
    -0.65
    ByPrimaryKey
    -0.65
     correctes
    -0.62
    WithMany
    -0.62
    脚注の使い方
    -0.61
    RegistryLite
    -0.58
     Wiktionnaire
    -0.58
    +#+#
    -0.56
    minton
    -0.56
    POSITIVE LOGITS
    <bos>
    0.55
    QMetaType
    0.54
     Jeden
    0.49
    oches
    0.48
     saites
    0.47
    chufe
    0.46
     mourut
    0.46
    ":[{
    0.46
     voci
    0.44
     Wicidata
    0.43
    Activations Density 2.601%

    No Known Activations