© 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
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 771
    Prev
    Next
    INDEX
    Explanations

    words and phrases frequently found adjacent to 'the' and 'internet'

    oai_token-act-pair · gemini-2.0-flash

    internet mentions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     HasFactory
    -0.62
    __":
    -0.55
    __':
    -0.47
    abá
    -0.46
    \{\\
    -0.46
    RegressionTest
    -0.45
    发表于
    -0.45
    étaire
    -0.44
    ongyang
    -0.43
     تضيفلها
    -0.43
    POSITIVE LOGITS
    Хьажоргаш
    0.66
    出版年
    0.61
     ISNI
    0.57
     web
    0.57
     arşivlendi
    0.56
    FunctionFlags
    0.55
    tehende
    0.55
     betweenstory
    0.54
     voltam
    0.54
     fantaisie
    0.54
    Activations Density 3.373%

    No Known Activations