© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13199
    Prev
    Next
    INDEX
    Explanations

    hyphens and possibly some associated numbers.

    oai_token-act-pair · gemini-2.0-flash

    document snippets/formatting marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    ValueStyle
    -0.34
    достатки
    -0.34
    bilirsiniz
    -0.33
    Answer
    -0.32
    Yesterday
    -0.32
    onAttach
    -0.32
     aanv
    -0.32
     bedoeld
    -0.32
    tığı
    -0.31
    didSet
    -0.31
    POSITIVE LOGITS
    はじめに
    0.48
     cherchés
    0.47
     <=",
    0.46
    <bos>
    0.46
    ///</
    0.45
     Normdatei
    0.43
     reiz
    0.43
    CJK
    0.41
    üyada
    0.40
    esi
    0.40
    Activations Density 2.357%

    No Known Activations