© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 9863
    Prev
    Next
    INDEX
    Explanations

    spanish language articles/pronouns

    oai_token-act-pair · gemini-2.0-flash

    La

    np_max-act · gemini-2.0-flash

    La

    np_max-act-logits · gpt-5-mini
    Triggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     la
    -2.09
    <bos>
    -1.91
    La
    -1.48
     La
    -1.45
    la
    -1.13
     LA
    -1.02
     las
    -0.94
    LA
    -0.88
     ла
    -0.85
     los
    -0.70
    POSITIVE LOGITS
     feroit
    0.84
     leaſt
    0.81
     auroit
    0.77
     فريبيس
    0.77
     myſelf
    0.75
     ſeveral
    0.73
     étoit
    0.71
     sumpay
    0.70
     poffible
    0.70
     étoient
    0.69
    Activations Density 0.331%

    No Known Activations