© 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. 12146
    Prev
    Next
    INDEX
    Explanations

    words associated with the winter solstice and ancient celebrations

    oai_token-act-pair · gemini-2.0-flash

    technical or programming terms

    np_token-act-pair-logits · gpt-4o-mini
    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
     fusing
    -0.49
     grij
    -0.48
    ariate
    -0.47
     shogun
    -0.47
    ✨:
    -0.46
     "));
    -0.46
    ()]);
    -0.46
     gemein
    -0.45
     älskar
    -0.45
    URLException
    -0.45
    POSITIVE LOGITS
     CreateTagHelper
    0.83
    MemoryWarning
    0.72
    WithIOException
    0.66
     ujednoznacz
    0.64
     متعلقه
    0.57
    lapsingToolbar
    0.57
    UnknownFieldSet
    0.57
    rungsseite
    0.57
    CodeAttribute
    0.57
    ApiModel
    0.56
    Activations Density 1.377%

    No Known Activations