© 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. 5395
    Prev
    Next
    INDEX
    Explanations

    items that are one or two of something as attributes

    oai_token-act-pair · gemini-2.0-flash

    tokens related to sizes and measurements

    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
    StoryboardSegue
    -0.80
     nahilalakip
    -0.79
    ंदीखरीदारी
    -0.73
    SpringBootTest
    -0.72
     Monfieur
    -0.71
    TagMode
    -0.70
    windowFixed
    -0.70
    yntaxException
    -0.69
    StructEnd
    -0.69
     مواليد
    -0.69
    POSITIVE LOGITS
     hole
    0.52
     row
    0.51
     stage
    0.50
     Row
    0.49
     piece
    0.49
     holes
    0.47
     side
    0.46
    спа
    0.45
     levels
    0.44
    Phương
    0.44
    Activations Density 1.584%

    No Known Activations