© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 577
    Prev
    Next
    INDEX
    Explanations

    words describing an event and later mentioning of an award

    oai_token-act-pair · gemini-2.0-flash

    awards and honors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    accumulative
    -0.61
     CreateTagHelper
    -0.59
    WithIOException
    -0.58
    שְׁ
    -0.57
     Thad
    -0.54
     forecasting
    -0.53
     bullies
    -0.52
     spokespersons
    -0.51
     theſe
    -0.51
     Correspond
    -0.51
    POSITIVE LOGITS
     يتيمه
    0.72
     []:
    0.59
    WriteBarrier
    0.56
    WidgetItem
    0.52
     تضيفلها
    0.52
    //
    0.51
     پذیر
    0.50
    تمبر
    0.49
     pós
    0.49
     quedado
    0.48
    Activations Density 1.602%

    No Known Activations