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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13012
    Prev
    Next
    INDEX
    Explanations

    references to dates, elections, and government in Nigerian news articles

    oai_token-act-pair · gemini-2.0-flash

    military-related terms

    np_token-act-pair-logits · gpt-4o-mini

    military, armies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    oa̍t
    -0.56
    ChildScrollView
    -0.52
     виправивши
    -0.51
     دیکھیے
    -0.51
    اریخ
    -0.50
    __*/
    -0.49
    AutoScaleMode
    -0.49
     nghiệp
    -0.47
    droje
    -0.46
    JsonIgnore
    -0.46
    POSITIVE LOGITS
     military
    0.61
     MILITARY
    0.60
     army
    0.59
     militer
    0.59
     ویکی‌پدیا
    0.57
     militaire
    0.56
     Junta
    0.56
    military
    0.53
     juntas
    0.52
    AsStream
    0.52
    Activations Density 1.343%

    No Known Activations