© 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. 388
    Prev
    Next
    INDEX
    Explanations

    decimal-separated numbers

    oai_token-act-pair · gemini-2.0-flash

    period

    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
     يتيمه
    -0.94
    StoryboardSegue
    -0.83
    DataAnnotations
    -0.81
    ftagPool
    -0.78
    InputBorder
    -0.71
    قایناقلار
    -0.71
    DoubleQuotes
    -0.68
    EndInit
    -0.67
    StoreMessageInfo
    -0.67
     الاطلاع
    -0.67
    POSITIVE LOGITS
    pecker
    0.47
    isMethod
    0.43
     verke
    0.42
    Sistem
    0.41
    vesti
    0.39
     conquête
    0.38
     laba
    0.38
    цезда
    0.37
    rometry
    0.36
    דר
    0.36
    Activations Density 0.037%

    No Known Activations