© 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. 6151
    Prev
    Next
    INDEX
    Explanations

    words associated with academic writing or scientific research

    oai_token-act-pair · gemini-2.0-flash

    technical/formal context

    np_max-act · gemini-2.0-flash
    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
    matchCondition
    -0.85
     <>",
    -0.71
    destroyAll
    -0.68
    thée
    -0.67
     beginnetje
    -0.66
     configureStore
    -0.65
    <bos>
    -0.65
    CloseOperation
    -0.64
    Сек
    -0.64
    OrBuilder
    -0.62
    POSITIVE LOGITS
    存于互联网档案馆
    0.53
     собой
    0.52
     собою
    0.50
    mery
    0.46
    Архівовано
    0.45
     laude
    0.44
    kshake
    0.44
     téléphonique
    0.43
    └──
    0.41
     ساله
    0.41
    Activations Density 3.406%

    No Known Activations