© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7188
    Prev
    Next
    INDEX
    Explanations

    numerical data including decimals and percentages

    oai_token-act-pair · gemini-2.0-flash

    numbers and percentages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    rawDesc
    -0.65
    }{*}{}
    -0.50
    IntentFilter
    -0.49
    ManagedBean
    -0.48
    DEAL
    -0.46
    vud
    -0.46
     im
    -0.45
    周泽楷
    -0.43
     onAnimation
    -0.43
     OnInit
    -0.43
    POSITIVE LOGITS
    LookAnd
    0.63
    antaranya
    0.62
    LEncoder
    0.59
    Chham
    0.57
     autorytatywna
    0.56
    Демографія
    0.56
     ویکی‌پدی
    0.55
    StackSize
    0.55
    IVEREF
    0.54
    TryDecodeAsNil
    0.52
    Activations Density 0.794%

    No Known Activations