© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12345
    Prev
    Next
    INDEX
    Explanations

    code or mathematical expressions, often in LaTeX format and/or related to databases

    oai_token-act-pair · gemini-2.0-flash

    parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     itſelf
    -1.09
     myſelf
    -1.01
     Efq
    -0.98
     themſelves
    -0.98
     Monfieur
    -0.92
     iſt
    -0.90
     houſe
    -0.86
     ſeveral
    -0.85
     reaſon
    -0.82
     Jefus
    -0.82
    POSITIVE LOGITS
    IGraphics
    0.57
    <eos>
    0.51
    <bos>
    0.49
    expandindo
    0.48
    detti
    0.47
     he
    0.43
    WriteAttribute
    0.43
    textTheme
    0.41
     go
    0.39
    ,
    0.39
    Activations Density 2.721%

    No Known Activations