© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3413
    Prev
    Next
    INDEX
    Explanations

    mentions of Cold War-era US foreign policy, interventions, and related figures or countries.

    oai_token-act-pair · gemini-2.0-flash

    Soviet Union

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    Erreferentziak
    -0.73
    ulemon
    -0.69
     ujednoznacz
    -0.66
     végétal
    -0.66
     doInBackground
    -0.66
     Millennium
    -0.65
     VEGF
    -0.65
    IGraphics
    -0.64
     JpaRepository
    -0.64
    RenderAtEndOf
    -0.63
    POSITIVE LOGITS
     Soviet
    0.75
    Soviet
    0.66
     USSR
    0.65
     Soviets
    0.60
     jugos
    0.56
     EdgeInsets
    0.54
    USSR
    0.53
     postwar
    0.51
     soviet
    0.51
     sovi
    0.50
    Activations Density 6.005%

    No Known Activations