© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12039
    Prev
    Next
    INDEX
    Explanations

    sentences where someone is considering something

    oai_token-act-pair · gemini-2.0-flash

    references to comprehension or understanding

    np_token-act-pair-logits · gpt-4o-mini

    Understanding and knowing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     layui
    -0.68
     ChromeDriver
    -0.60
     jScrollPane
    -0.56
    Jeografia
    -0.55
     THOUGHTS
    -0.53
     Dreyfus
    -0.52
    preuves
    -0.49
    ienka
    -0.49
    chromedriver
    -0.49
    hésite
    -0.48
    POSITIVE LOGITS
    Personendaten
    0.68
    ViewFeatures
    0.60
     cotton
    0.51
     realize
    0.50
     grasp
    0.50
    cotton
    0.50
     realizes
    0.50
    SafeMath
    0.49
    věř
    0.47
     '*')
    0.47
    Activations Density 3.379%

    No Known Activations