© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3141
    Prev
    Next
    INDEX
    Explanations

    words related to national organizations and security

    oai_token-act-pair · gemini-2.0-flash

    National Geographic or security

    np_max-act · gemini-2.0-flash

    National

    np_max-act-logits · gpt-5-mini
    Triggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ADELPHIA
    -0.75
    TIMORE
    -0.73
    CONSIN
    -0.71
    ROIT
    -0.65
    ANSAS
    -0.59
     Chicago
    -0.57
     America
    -0.57
    America
    -0.57
    WAUKEE
    -0.57
     Oklahoma
    -0.56
    POSITIVE LOGITS
    InstrumentedTest
    0.69
    الدراسه
    0.63
     kaynağından
    0.63
     pubb
    0.60
     /\.
    0.59
     GoogleFonts
    0.59
     Vikipedi
    0.58
    linson
    0.57
     PROGRAMME
    0.57
     Commando
    0.56
    Activations Density 1.074%

    No Known Activations