© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12653
    Prev
    Next
    INDEX
    Explanations

    Japanese language text, specifically sentence-ending particles and words indicating possibility

    oai_token-act-pair · gemini-2.0-flash

    が

    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
    が
    -1.02
    가
    -0.89
     が
    -0.78
    りが
    -0.73
    さんが
    -0.60
    みが
    -0.59
    이
    -0.59
    子が
    -0.57
    氏が
    -0.56
    がこの
    -0.56
    POSITIVE LOGITS
     CreateTagHelper
    0.64
    ADVERTISEMENT
    0.63
     arşivlendi
    0.57
    rawDesc
    0.56
     समीक्षाओं
    0.55
     onBackPressed
    0.55
     corpi
    0.54
     userDao
    0.54
    enumi
    0.53
    tvguidetime
    0.52
    Activations Density 5.802%

    No Known Activations