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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14554
    Prev
    Next
    INDEX
    Explanations

    mentions of operating systems and applications, especially in the context of availability and development.

    oai_token-act-pair · gemini-2.0-flash

    software and operating systems

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     android
    -1.18
     apple
    -1.16
     facebook
    -1.05
     google
    -1.03
     windows
    -1.03
     adobe
    -0.99
    google
    -0.96
    android
    -0.95
     youtube
    -0.95
    windows
    -0.94
    POSITIVE LOGITS
     femininas
    0.63
    RenderAtEndOf
    0.61
     brancas
    0.59
     vermelhas
    0.59
    TestingModule
    0.54
    ArgumentParser
    0.53
     colectiva
    0.53
     initComponents
    0.50
     culturelles
    0.50
     Paglinawan
    0.50
    Activations Density 7.686%

    No Known Activations