© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5605
    Prev
    Next
    INDEX
    Explanations

    html and javascript code related to website formatting

    oai_token-act-pair · gemini-2.0-flash

    code

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

    No Comments

    Negative Logits
    ’
    -0.48
    ↵↵
    -0.47
     often
    -0.46
    <bos>
    -0.45
     default
    -0.45
    `
    -0.44
    мар
    -0.43
    '
    -0.41
    .
    -0.40
     T
    -0.40
    POSITIVE LOGITS
    InjectAttribute
    1.16
     незавершена
    1.15
     ویکی‌پدیا
    1.11
    EndInit
    1.06
    ResumeLayout
    0.99
    Geplaatst
    0.99
    Datuak
    0.96
    complexContent
    0.93
     AssemblyCulture
    0.92
     Мексичка
    0.92
    Activations Density 0.134%

    No Known Activations