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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 6506
    Prev
    Next
    INDEX
    Explanations

    capitalized "Ly" in various contexts, which could be the beginning of a word or name

    oai_token-act-pair · gemini-2.0-flash

    tokens starting with 'Ly'

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

    Ly

    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
     nakalista
    -0.64
    nonatomic
    -0.47
     تضيفلها
    -0.46
    topf
    -0.46
     Edizioni
    -0.45
    <()>
    -0.45
     Weld
    -0.45
    replaceAll
    -0.44
    replace
    -0.43
    Решение
    -0.43
    POSITIVE LOGITS
    SequentialGroup
    0.75
     ویکی‌پدیای
    0.74
     DialogInterface
    0.66
    forChild
    0.63
    TargetException
    0.62
    InjectAttribute
    0.62
    }],
    
    0.62
     kasarigan
    0.59
     للاسماء
    0.58
    StoryboardSegue
    0.58
    Activations Density 0.176%

    No Known Activations