© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15383
    Prev
    Next
    INDEX
    Explanations

    mentions of erectile dysfunction and the drug Viagra

    oai_token-act-pair · gemini-2.0-flash

    terms related to erectile dysfunction

    np_token-act-pair-logits · gpt-4o-mini

    sexual content

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    tagHelperRunner
    -1.03
    InstrumentedTest
    -0.61
     صوتيه
    -0.54
    ViewFeatures
    -0.54
     ✭✭
    -0.51
     بيها
    -0.50
     kaarangay
    -0.49
    terday
    -0.49
     itong
    -0.49
    toon
    -0.48
    POSITIVE LOGITS
    NameInMap
    0.59
    Diwedd
    0.59
     HasFactory
    0.54
    ViewImports
    0.53
    ">${
    0.51
     kasarigan
    0.50
    ContentValues
    0.48
     disambiguazione
    0.47
     Himo
    0.47
     TextInputType
    0.47
    Activations Density 0.508%

    No Known Activations