© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11464
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to conflict, competition or contracts.

    oai_token-act-pair · gemini-2.0-flash

    say "in" words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    rawDesc
    -0.56
    aktery
    -0.50
     allAfrica
    -0.50
    OCCURRED
    -0.48
    MethodManager
    -0.47
     Calabria
    -0.47
    chauss
    -0.47
    határoz
    -0.46
    onshire
    -0.46
    iotto
    -0.46
    POSITIVE LOGITS
     in
    1.24
     dalam
    0.72
    ใน
    0.71
    migrationBuilder
    0.71
     trong
    0.66
     في
    0.65
     nelle
    0.63
     در
    0.63
     nella
    0.63
     în
    0.62
    Activations Density 1.831%

    No Known Activations