© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 3734
    Prev
    Next
    INDEX
    Explanations

    verbs being performed or experienced such as "blowing" or "off"

    oai_token-act-pair · gemini-2.0-flash

    Wind/openings

    np_max-act · gemini-2.0-flash

    blow

    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_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     nakalista
    -0.59
     au
    -0.50
    lardır
    -0.46
     contém
    -0.46
    <eos>
    -0.44
     Fuß
    -0.40
     le
    -0.40
     par
    -0.40
    ждый
    -0.39
    हि
    -0.39
    POSITIVE LOGITS
    StoryboardSegue
    1.15
     архивлан
    1.04
     <>",
    1.02
    MessageTagHelper
    0.99
    IUrlHelper
    0.96
    DockStyle
    0.94
     AssemblyTitle
    0.94
    setVerticalGroup
    0.93
     ―――――
    0.93
    IonicModule
    0.92
    Activations Density 2.698%

    No Known Activations