© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13109
    Prev
    Next
    INDEX
    Explanations

    html code, or code-like text including keywords such as charset width, height, jsonobject, href, and https

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    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
    aarrggbb
    -0.92
    :✨
    -0.89
    writeFieldEnd
    -0.88
    migrationBuilder
    -0.73
     resourceCulture
    -0.70
    Хьажоргаш
    -0.66
     nakalista
    -0.66
    TypedDataSet
    -0.66
    таратура
    -0.65
    DriverManager
    -0.65
    POSITIVE LOGITS
     flamen
    0.45
    mphony
    0.43
    ONU
    0.43
     dolphins
    0.40
    cluye
    0.39
     Sixt
    0.39
    Pixels
    0.39
     symptoms
    0.39
    queiro
    0.39
    lesias
    0.39
    Activations Density 3.168%

    No Known Activations