© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3341
    Prev
    Next
    INDEX
    Explanations

    code or data related to arrays, special characters, or pattern matching

    oai_token-act-pair · gemini-2.0-flash

    nonsensical text/code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    -0.88
    AddTagHelper
    -0.77
     FetchType
    -0.63
    eſt
    -0.59
    ovsk
    -0.57
    enthal
    -0.56
    fillType
    -0.54
     CreateTagHelper
    -0.54
    aarrggbb
    -0.53
    readystatechange
    -0.53
    POSITIVE LOGITS
     שוליים
    0.51
     religieuse
    0.50
    TestTools
    0.49
    :✨
    0.49
     personalità
    0.48
     {;
    0.48
    BorderStyle
    0.47
     scream
    0.47
     мәкал
    0.46
    messageInfo
    0.46
    Activations Density 0.570%

    No Known Activations