© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 14031
    Prev
    Next
    INDEX
    Explanations

    the word "dense" and variants or misspellings of it

    oai_token-act-pair · gemini-2.0-flash

    dense

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    di
    -0.47
     di
    -0.45
    x
    -0.45
     string
    -0.43
    div
    -0.43
     pula
    -0.43
     dine
    -0.41
    por
    -0.41
    dom
    -0.41
    '
    -0.40
    POSITIVE LOGITS
    PerformLayout
    1.16
     بيها
    0.98
    StoryboardSegue
    0.98
    makeConstraints
    0.96
    IntoConstraints
    0.94
     المعيارى
    0.94
     >=",
    0.91
    ParallelGroup
    0.91
    ⓧ
    0.88
     تضيفلها
    0.84
    Activations Density 0.217%

    No Known Activations