© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 9890
    Prev
    Next
    INDEX
    Explanations

    the word "just" and words near it

    oai_token-act-pair · gemini-2.0-flash

    just

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     initComponents
    -0.68
    PropertyGroup
    -0.66
    httphttps
    -0.62
    SourceChecksum
    -0.57
    principalTable
    -0.56
     >=",
    -0.54
     defaultstate
    -0.54
    awtextra
    -0.49
    AddTagHelper
    -0.49
    ########.
    -0.48
    POSITIVE LOGITS
     ſmall
    0.59
     ſtill
    0.59
     pleaſure
    0.58
     juſt
    0.56
     assuming
    0.55
     reaſon
    0.54
     ſeveral
    0.54
     uſed
    0.53
    exitRule
    0.53
     feathers
    0.53
    Activations Density 5.094%

    No Known Activations