© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5604
    Prev
    Next
    INDEX
    Explanations

    words related to political agreements

    oai_token-act-pair · gemini-2.0-flash

    agreements and deals

    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
     "..\..\
    -0.93
    JspWriter
    -0.88
    Хьажоргаш
    -0.84
     contextLoads
    -0.77
    GraphicsUnit
    -0.77
     AdapterView
    -0.75
    ScopeManager
    -0.73
    таратура
    -0.72
    aarrggbb
    -0.72
     ""],
    -0.71
    POSITIVE LOGITS
    ol
    0.54
     worked
    0.46
    lo
    0.42
     reached
    0.41
    OW
    0.41
     initial
    0.39
    OL
    0.39
     covering
    0.38
     IR
    0.38
     lo
    0.38
    Activations Density 3.739%

    No Known Activations