© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11614
    Prev
    Next
    INDEX
    Explanations

    LaTeX markup for mathematical equations

    oai_token-act-pair · gemini-2.0-flash

    mathematical notation and variables

    np_token-act-pair-logits · gpt-4o-mini

    _{

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     архивлан
    -0.76
     initComponents
    -0.69
    ükü
    -0.59
    Vidite
    -0.57
    unächst
    -0.54
    </tfoot>
    -0.54
    """,
    -0.53
     makl
    -0.53
    InSection
    -0.52
    */),
    -0.52
    POSITIVE LOGITS
     оригіналу
    0.60
    n
    0.54
     lead
    0.52
    lead
    0.52
    MethodManager
    0.48
     deportivas
    0.47
     insuffisamment
    0.46
    SharedCtor
    0.46
    AntiForgeryToken
    0.43
     ContentValues
    0.42
    Activations Density 3.331%

    No Known Activations