© 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. 1064
    Prev
    Next
    INDEX
    Explanations

    words related to conflict, political power, and loyalty within a historical region

    oai_token-act-pair · gemini-2.0-flash

    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_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
     Wilkins
    -0.54
     Dickerson
    -0.52
     Stapleton
    -0.51
     Beattie
    -0.51
     Stephenson
    -0.51
     William
    -0.51
     McAllister
    -0.51
    umumkan
    -0.50
     McCullough
    -0.49
     Langford
    -0.49
    POSITIVE LOGITS
     Imam
    0.65
     Uy
    0.63
     Khas
    0.62
     Hij
    0.62
     Kyrgyz
    0.61
     Uz
    0.61
     Sinh
    0.60
     Khmer
    0.60
     Nazar
    0.58
     Niz
    0.58
    Activations Density 75.813%

    No Known Activations