© 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
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 13105
    Prev
    Next
    INDEX
    Explanations

    titles of academic publications in economics or statistics

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    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
    fromCharCode
    -0.54
    WithIOException
    -0.44
    PerformLayout
    -0.39
    ByVersion
    -0.39
    CodeDom
    -0.39
     peix
    -0.39
    我不知道
    -0.39
    (!__
    -0.39
    MessageOf
    -0.39
    IVEREF
    -0.39
    POSITIVE LOGITS
    UserScript
    0.70
     Efq
    0.65
     Perſ
    0.65
    khana
    0.60
     Houſe
    0.60
     Reſ
    0.59
     mids
    0.57
    TestTools
    0.57
     Conſ
    0.57
     houſe
    0.56
    Activations Density 0.765%

    No Known Activations