© 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
    2. Gemma-2-2B
    3. 8-GEMMASCOPE-TRANSCODER-16K
    4. 1246
    Prev
    Next
    INDEX
    Explanations

    language related to conflict, be it personal, cultural, or political.

    oai_token-act-pair · gemini-2.0-flash

    online discussion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     ویکی‌آمباردا
    -0.49
     voulu
    -0.45
     tiết
    -0.45
     keyPressed
    -0.44
    letal
    -0.44
     restriction
    -0.43
     cool
    -0.43
     sáng
    -0.43
     conflict
    -0.42
    ybės
    -0.42
    POSITIVE LOGITS
     AssemblyCompany
    0.74
    andExpect
    0.71
    IonicModule
    0.64
     للاسماء
    0.63
     AssemblyCulture
    0.59
    missing
    0.59
    OGND
    0.59
     missing
    0.59
     Missing
    0.58
    ConstraintMaker
    0.57
    Activations Density 20.767%

    No Known Activations