© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9598
    Prev
    Next
    INDEX
    Explanations

    words and phrases of greeting in different languages, especially French, along with terms related to fantasy and religion

    oai_token-act-pair · gemini-2.0-flash

    bonjour

    np_max-act · gemini-2.0-flash

    ▁bonjour

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     luffy
    -0.97
     stockholm
    -0.88
     gopro
    -0.82
     tibet
    -0.82
     barcelona
    -0.81
     ferrari
    -0.81
    Packard
    -0.79
     venice
    -0.79
    knapp
    -0.79
    Barbados
    -0.78
    POSITIVE LOGITS
     enfans
    1.13
     déchir
    1.08
     dieux
    1.05
     plais
    1.04
     larmes
    1.04
     démocr
    1.01
     oreilles
    1.00
     espirituales
    1.00
    VELOP
    1.00
     tű
    0.98
    Activations Density 12.223%

    No Known Activations