© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 16239
    Prev
    Next
    INDEX
    Explanations

    text related to US foreign policy and economic intervention in Latin America.

    oai_token-act-pair · gemini-2.0-flash

    International relations and politics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    GHIJKLM
    -0.49
    Становништво
    -0.45
    assertj
    -0.43
    ựng
    -0.42
    glUniform
    -0.41
     Wicidata
    -0.41
    PerformLayout
    -0.41
    وفاته
    -0.41
     اشت
    -0.40
     KeyEvent
    -0.40
    POSITIVE LOGITS
    ImageContext
    0.70
     dataSnapshot
    0.61
    存于互联网档案馆
    0.59
    SequentialGroup
    0.58
    WriteLiteral
    0.58
    wapV
    0.57
    expandindo
    0.56
    ersham
    0.56
    CASCADE
    0.56
     (;;
    0.55
    Activations Density 1.408%

    No Known Activations