© 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. 7416
    Prev
    Next
    INDEX
    Explanations

    dates, merges, annexations of political entities

    oai_token-act-pair · gemini-2.0-flash

    merge

    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
     domo
    -0.47
    frente
    -0.42
    Share
    -0.40
     Stevens
    -0.40
     panjang
    -0.40
    seg
    -0.39
     envía
    -0.39
    スタン
    -0.39
    نيف
    -0.39
     زم
    -0.38
    POSITIVE LOGITS
     merger
    1.00
     merged
    0.98
     integration
    0.96
     dissolving
    0.96
     merging
    0.96
     merge
    0.96
     dissolve
    0.95
     integrate
    0.94
     dissolves
    0.92
     dissolution
    0.92
    Activations Density 1.049%

    No Known Activations