© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10687
    Prev
    Next
    INDEX
    Explanations

    quotations and phrases that include commas

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     betweenstory
    -0.95
     Мексичка
    -0.93
    DockStyle
    -0.85
    GraphicsUnit
    -0.84
     BoxDecoration
    -0.79
    İstinadlar
    -0.78
    RegressionTest
    -0.76
    EndProject
    -0.74
     >=",
    -0.74
    BoxShadow
    -0.74
    POSITIVE LOGITS
      
    0.42
     interest
    0.38
    My
    0.37
    A
    0.35
    ↵
    0.35
    '
    0.35
     or
    0.35
        
    0.34
    *
    0.34
    <em>
    0.34
    Activations Density 0.869%

    No Known Activations