© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14061
    Prev
    Next
    INDEX
    Explanations

    terms related to menus and data relations

    oai_token-act-pair · gemini-2.0-flash

    menu

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     menu
    -2.36
    menu
    -2.19
     Menu
    -2.13
    Menu
    -2.03
     menus
    -1.84
     MENU
    -1.76
    MENU
    -1.59
     Menus
    -1.55
     menú
    -1.48
     меню
    -1.48
    POSITIVE LOGITS
    ########.
    0.75
     Efq
    0.73
    parsedMessage
    0.67
    FieldBuilder
    0.65
    Personensuche
    0.65
     fotográfica
    0.63
     متعلقه
    0.61
     Monfieur
    0.61
     resourceCulture
    0.60
     fairest
    0.59
    Activations Density 6.700%

    No Known Activations