© 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. 12663
    Prev
    Next
    INDEX
    Explanations

    mentions of "British", "American", or the UK

    oai_token-act-pair · gemini-2.0-flash

    references to the UK or British entities

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

    British

    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
     adaptée
    -0.58
     immédi
    -0.52
     beginnetje
    -0.48
     referrerpolicy
    -0.46
    maßen
    -0.46
    contentLoaded
    -0.46
     spør
    -0.46
     intermédiaire
    -0.46
    YourGuide
    -0.45
     adaptar
    -0.45
    POSITIVE LOGITS
    gameserver
    0.67
    TagMode
    0.61
    runApp
    0.56
    assies
    0.56
    Personendaten
    0.55
    errmsg
    0.54
    UnitTesting
    0.54
    revalidate
    0.53
    AxisAlignment
    0.52
    cplusplus
    0.52
    Activations Density 0.754%

    No Known Activations