© 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. 11427
    Prev
    Next
    INDEX
    Explanations

    LaTeX math notation, especially variable names

    oai_token-act-pair · gemini-2.0-flash

    Code and math formulas

    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
     Dampf
    -0.42
     מים
    -0.42
    Buen
    -0.42
     TAMBÉM
    -0.42
    chaun
    -0.40
    EXAMPLES
    -0.39
    enumii
    -0.39
    argento
    -0.39
     kaynağından
    -0.38
     yeşil
    -0.38
    POSITIVE LOGITS
    AnchorTagHelper
    0.72
    abetes
    0.69
     متعلقه
    0.68
    withIdentifier
    0.68
     يتيمه
    0.68
    MigrationBuilder
    0.66
    sizeCache
    0.66
    PreferredItem
    0.65
    LEncoder
    0.65
    UserScript
    0.64
    Activations Density 6.562%

    No Known Activations