© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9797
    Prev
    Next
    INDEX
    Explanations

    sentence fragments with forms of 'is' or 'are' followed by an article

    oai_token-act-pair · gemini-2.0-flash

    is/are

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ared
    -0.55
    neuf
    -0.55
    nlm
    -0.51
    知的
    -0.47
    nival
    -0.47
    ativit
    -0.44
    STE
    -0.44
     procu
    -0.43
     asas
    -0.43
    mated
    -0.41
    POSITIVE LOGITS
     kaarangay
    0.79
    GOTREF
    0.74
    تقاوى
    0.71
     Мексичка
    0.66
    PreInfinity
    0.66
     Signalez
    0.62
     ExecuteAsync
    0.60
    NewUrlParser
    0.59
    xaml
    0.59
    Демографія
    0.59
    Activations Density 2.143%

    No Known Activations