© 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. 12499
    Prev
    Next
    INDEX
    Explanations

    initialisms and acronyms, especially those related to institutions and companies

    oai_token-act-pair · gemini-2.0-flash

    abbreviations

    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
    enumi
    -0.49
    isir
    -0.45
    aris
    -0.44
     is
    -0.43
    ంత
    -0.42
    <bos>
    -0.42
     effet
    -0.41
    kor
    -0.41
    sterone
    -0.41
     r
    -0.40
    POSITIVE LOGITS
     purpoſe
    0.73
     Réponses
    0.70
    rrggbb
    0.64
     EconPapers
    0.64
     ſeveral
    0.63
     disambiguazione
    0.63
     myſelf
    0.63
    astéroïdes
    0.63
     leaſt
    0.62
    writeField
    0.61
    Activations Density 0.519%

    No Known Activations