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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6358
    Prev
    Next
    INDEX
    Explanations

    the letters "-age," the letters "-in," and the letter "y."

    oai_token-act-pair · gemini-2.0-flash

    Short letter combinations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -1.34
    kháu
    -0.85
     an
    -0.70
    expandindo
    -0.67
     it
    -0.64
    Билгалдахарш
    -0.62
    Autoritní
    -0.60
    `]
    -0.59
    ')")
    -0.58
     the
    -0.57
    POSITIVE LOGITS
     Al
    0.69
     valleys
    0.60
     neighborhoods
    0.58
     al
    0.58
     Enrollment
    0.57
    Aligned
    0.57
     alphabetically
    0.57
     equalizer
    0.55
     Alameda
    0.55
     Todos
    0.55
    Activations Density 2.756%

    No Known Activations