© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11556
    Prev
    Next
    INDEX
    Explanations

    legal and programming jargon

    oai_token-act-pair · gemini-2.0-flash

    legal/technical documentation

    np_max-act · gemini-2.0-flash
    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
    Not in Any Lists

    No Comments

    Negative Logits
    contentLoaded
    -1.05
    ViewImports
    -0.88
    ReusableCell
    -0.85
     HttpNotFound
    -0.80
    WebControls
    -0.77
    rzost
    -0.73
    IBar
    -0.73
    DockStyle
    -0.72
    ValueGenerated
    -0.72
     AssemblyVersion
    -0.71
    POSITIVE LOGITS
    <bos>
    0.59
      
    0.42
    -
    0.37
     same
    0.36
    flashdata
    0.36
    همان
    0.36
    χη
    0.35
     crit
    0.35
     mismo
    0.35
    urable
    0.34
    Activations Density 0.857%

    No Known Activations