© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4149
    Prev
    Next
    INDEX
    Explanations

    capitalized words related to political entities, especially heads of state, and their associations

    oai_token-act-pair · gemini-2.0-flash

    terms related to prime ministers and leadership

    np_token-act-pair-logits · gpt-4o-mini

    Prime ministers/leaders

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
     CURIAM
    -0.68
    Filmo
    -0.68
     متعلقه
    -0.68
     crois
    -0.62
     onCreateView
    -0.57
     themſelves
    -0.57
    gameserver
    -0.55
     estimés
    -0.54
    جغرافيا
    -0.54
    EndInit
    -0.54
    POSITIVE LOGITS
     prime
    0.83
     Prime
    0.82
    Prime
    0.70
     leaders
    0.70
    prime
    0.68
    PRIME
    0.66
     PM
    0.63
     Premier
    0.62
    leaders
    0.58
     premier
    0.57
    Activations Density 2.623%

    No Known Activations