© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11315
    Prev
    Next
    INDEX
    Explanations

    terms related to documentation, software development, and web technologies.

    oai_token-act-pair · gemini-2.0-flash

    document

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    rungsseite
    -0.97
    MessageOf
    -0.85
    sizeCache
    -0.82
    AnimationsModule
    -0.75
    ArrowToggle
    -0.73
    UserScript
    -0.72
     متعلقه
    -0.71
    ########.
    -0.71
    AndEndTag
    -0.69
    webElementXpaths
    -0.68
    POSITIVE LOGITS
     generaciones
    0.45
    fseek
    0.43
     урна
    0.43
    Климат
    0.41
    ues
    0.38
    agisse
    0.38
     ba
    0.37
    ати
    0.37
    fok
    0.37
    Intent
    0.36
    Activations Density 6.453%

    No Known Activations