Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14234
    Prev
    Next
    INDEX
    Explanations

    references to faith, morals, public service and political campaigns

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.96
    ^(@)
    -0.95
     Anſ
    -0.94
    脚注の使い方
    -0.90
    saraba
    -0.90
    PerformLayout
    -0.89
     CreateTagHelper
    -0.88
    Personensuche
    -0.88
    الحياه
    -0.87
    èdia
    -0.87
    POSITIVE LOGITS
     us
    0.54
     me
    0.45
    не
    0.44
    V
    0.43
     V
    0.42
     luce
    0.41
    ,
    0.41
     Anna
    0.40
    `
    0.40
     le
    0.40
    Activations Density 4.106%

    No Known Activations