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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6671
    Prev
    Next
    INDEX
    Explanations

    words that are related to administrative or corporate documents.

    oai_token-act-pair · gemini-2.0-flash

    say "space" words

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     Houſe
    -0.86
    ſelf
    -0.81
    Datuak
    -0.80
    ſelves
    -0.77
     tfsi
    -0.76
    MLLoader
    -0.73
     Corée
    -0.72
     moschino
    -0.72
    σθαι
    -0.71
     quæ
    -0.71
    POSITIVE LOGITS
    <bos>
    0.71
     transférez
    0.64
    expandindo
    0.56
     sem
    0.54
    twimg
    0.54
     hal
    0.52
     op
    0.51
    ↵↵
    0.51
     sé
    0.51
     er
    0.49
    Activations Density 6.913%

    No Known Activations