© 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. 7856
    Prev
    Next
    INDEX
    Explanations

    words used in reasoning or argumentation in legal or academic settings.

    oai_token-act-pair · 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
     Then
    -1.64
     Also
    -1.57
     Because
    -1.52
     That
    -1.52
     There
    -1.51
     Which
    -1.48
     They
    -1.48
     This
    -1.47
     When
    -1.47
     These
    -1.46
    POSITIVE LOGITS
    webElementXpaths
    0.64
     kasarigan
    0.56
     Fleet
    0.54
     Rail
    0.54
    istoitu
    0.53
     Económica
    0.53
     Medal
    0.51
     Bureau
    0.50
     Road
    0.49
     Público
    0.49
    Activations Density 47.922%

    No Known Activations