© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 16253
    Prev
    Next
    INDEX
    Explanations

    numbers, especially those involved in statistics, patents, calculation, or identification

    oai_token-act-pair · gemini-2.0-flash

    Technical documentation

    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
    mặt
    -0.40
     سكانية
    -0.35
    ładka
    -0.34
     Viitattu
    -0.32
     havaianas
    -0.32
    pprint
    -0.31
     Idd
    -0.30
    TUT
    -0.30
    ThroughAttribute
    -0.30
     Monfieur
    -0.30
    POSITIVE LOGITS
    bootstrapcdn
    0.86
    findpost
    0.82
    ✨:
    0.69
    DoubleQuotes
    0.68
    发表于
    0.66
     Vikipedi
    0.65
    出版年
    0.65
    6
    0.64
     оригіналу
    0.63
    4
    0.63
    Activations Density 53.997%

    No Known Activations