© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 5076
    Prev
    Next
    INDEX
    Explanations

    text referring to unfamiliar people witnessing and commenting on someone else's private affairs

    oai_token-act-pair · gemini-2.0-flash

    stranger

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    تقاوى
    -0.62
    DotNetBar
    -0.60
    encodeWith
    -0.59
    djangoproject
    -0.58
    onViewCreated
    -0.56
     resourceCulture
    -0.56
     Signalez
    -0.56
     مرئيه
    -0.56
    HEAST
    -0.55
     writeTo
    -0.55
    POSITIVE LOGITS
    <bos>
    0.52
     ¢
    0.49
    amentos
    0.48
    newArrayList
    0.42
    ➋
    0.41
    کل
    0.40
     Coliseum
    0.40
    יצד
    0.40
    piring
    0.40
    راتيج
    0.40
    Activations Density 0.497%

    No Known Activations