© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4941
    Prev
    Next
    INDEX
    Explanations

    mentions of countries and political entities, and events involving them

    oai_token-act-pair · gemini-2.0-flash

    official

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     dags
    -0.51
     cha
    -0.43
     Seni
    -0.42
    AutoField
    -0.41
    /**
    -0.41
    Cha
    -0.40
    ched
    -0.39
     chao
    -0.39
     Cha
    -0.38
    espère
    -0.38
    POSITIVE LOGITS
     official
    0.85
     condemnation
    0.84
    Official
    0.83
     condemn
    0.82
     condemning
    0.81
    OFFICIAL
    0.80
     condemned
    0.79
     oficial
    0.79
    official
    0.79
     oficjal
    0.78
    Activations Density 1.124%

    No Known Activations