© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9817
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to government, finances, and projects

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    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
     Plan
    -0.95
     plan
    -0.94
    Plan
    -0.80
     Project
    -0.77
     ExecuteAsync
    -0.76
    NUMX
    -0.73
     project
    -0.72
     PLAN
    -0.71
    plan
    -0.69
    PLAN
    -0.68
    POSITIVE LOGITS
     sério
    0.63
     pagare
    0.58
     zoos
    0.57
     puol
    0.56
     abstrato
    0.54
     stră
    0.53
     abstrait
    0.52
     Romney
    0.51
     uș
    0.50
     gypsy
    0.50
    Activations Density 11.068%

    No Known Activations