© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7318
    Prev
    Next
    INDEX
    Explanations

    some words in Portugese and Spanish, some Javascript terms, and a few random words in English

    oai_token-act-pair · gemini-2.0-flash

    Non-English code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     que
    -2.33
    que
    -1.87
     QUE
    -1.80
    Que
    -1.73
     Que
    -1.63
    QUE
    -1.41
     qu
    -1.13
     qui
    -1.00
    ques
    -0.87
    quea
    -0.86
    POSITIVE LOGITS
    SequentialGroup
    0.83
     فريبيس
    0.62
     noDo
    0.59
     externi
    0.58
     Normdatei
    0.56
    :✨
    0.56
     transférez
    0.54
     AssemblyCulture
    0.53
     poveznice
    0.51
    Зноскі
    0.50
    Activations Density 0.542%

    No Known Activations