© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 16380
    Prev
    Next
    INDEX
    Explanations

    various adjectival words in many different contexts.

    oai_token-act-pair · gemini-2.0-flash

    Translation of "to"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    tagHelper
    -0.74
    hasMoreElements
    -0.70
    ьаж
    -0.66
     referenties
    -0.66
    webElementXpaths
    -0.65
    ंदीखरीदारी
    -0.63
    chtenstein
    -0.62
    ajoz
    -0.62
     CreateTagHelper
    -0.62
    脚注の使い方
    -0.62
    POSITIVE LOGITS
     to
    2.88
    到
    1.32
    to
    1.16
    至
    1.00
     να
    0.93
    DataTo
    0.92
     إلى
    0.84
     至
    0.83
     到
    0.80
     kepada
    0.79
    Activations Density 7.169%

    No Known Activations