© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2799
    Prev
    Next
    INDEX
    Explanations

    mentions of pubs located in Bury, UK

    oai_token-act-pair · gemini-2.0-flash

    technical or programming terminology

    np_token-act-pair-logits · gpt-4o-mini

    locations and names

    np_max-act-logits · gemini-2.0-flash
    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
    ηγ
    -0.47
    addGroup
    -0.38
    ubov
    -0.37
     dür
    -0.36
    inander
    -0.35
    ومت
    -0.35
    sscanf
    -0.34
     Й
    -0.34
     y
    -0.34
     Mal
    -0.33
    POSITIVE LOGITS
     CreateTagHelper
    0.90
    RectangleBorder
    0.78
    mybatisplus
    0.77
    ViewFeatures
    0.68
    wikimedia
    0.66
    AnchorStyles
    0.63
    CppMethod
    0.63
     Waray
    0.63
    MemoryWarning
    0.63
     Deane
    0.62
    Activations Density 0.317%

    No Known Activations