© 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. 4461
    Prev
    Next
    INDEX
    Explanations

    verbs related to action or descriptions of actions in contexts where there might be opposing sides or conflict.

    oai_token-act-pair · gemini-2.0-flash

    action and relationship verbs

    np_max-act · gemini-2.0-flash

    verbs

    np_max-act-logits · gpt-5-mini
    Triggered by @chenshw0109
    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
     far
    -0.56
    TestTools
    -0.52
     Giải
    -0.46
     t
    -0.45
     pres
    -0.45
     deep
    -0.44
     ligne
    -0.43
     mengh
    -0.43
     Office
    -0.42
    <thead>
    -0.41
    POSITIVE LOGITS
     CreateTagHelper
    0.79
    IsMutable
    0.78
    writeFieldEnd
    0.77
    contentLoaded
    0.76
    CopyWith
    0.71
     Wicidata
    0.71
    verifyException
    0.66
    WithIOException
    0.63
    Erstellt
    0.63
    RegisterType
    0.62
    Activations Density 5.313%

    No Known Activations