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. 16228
    Prev
    Next
    INDEX
    Explanations

    words related to policy and healthcare legislation, as well as research and strategies

    oai_token-act-pair · gemini-2.0-flash

    plans and responses

    np_max-act-logits · 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
     CreateTagHelper
    -1.07
     مشين
    -0.98
    OrNil
    -0.94
     autorytatywna
    -0.93
    findpost
    -0.91
    EndInit
    -0.88
    حياتها
    -0.86
     beginnetje
    -0.85
    حياته
    -0.85
    PerformLayout
    -0.82
    POSITIVE LOGITS
     to
    1.29
     чтобы
    0.77
    to
    0.74
     щоб
    0.60
     aimed
    0.53
    来
    0.50
     để
    0.49
    來
    0.49
     upang
    0.47
     aiming
    0.47
    Activations Density 1.873%

    No Known Activations