© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13011
    Prev
    Next
    INDEX
    Explanations

    mentions of geopolitical conflict and international relations

    oai_token-act-pair · gemini-2.0-flash

    international relations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    textbackslash
    -0.47
    '][]
    -0.42
    migrationBuilder
    -0.41
    .*")]
    -0.41
    <bos>
    -0.41
     car
    -0.41
     most
    -0.41
    wiek
    -0.40
     start
    -0.38
     deleteById
    -0.38
    POSITIVE LOGITS
     Roskov
    0.82
     kasarigan
    0.79
    ########.
    0.72
     transfieras
    0.71
    TestBed
    0.68
    tvguidetime
    0.68
     Obrador
    0.67
    TestingModule
    0.65
    Identyfik
    0.65
    GraphicsUnit
    0.64
    Activations Density 0.351%

    No Known Activations