© 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. 13665
    Prev
    Next
    INDEX
    Explanations

    the suffix "ker" as part of swear words or smoker

    oai_token-act-pair · gemini-2.0-flash

    ker

    np_max-act · gemini-2.0-flash
    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
    Not in Any Lists

    No Comments

    Negative Logits
    ker
    -1.34
    KER
    -1.02
    kers
    -0.92
     ker
    -0.88
     Ker
    -0.84
    Ker
    -0.81
    ster
    -0.77
    STER
    -0.73
    kerne
    -0.71
    keri
    -0.70
    POSITIVE LOGITS
    <bos>
    1.73
    Хьажоргаш
    0.85
    InjectAttribute
    0.83
    URLException
    0.77
    Autoritní
    0.77
     Réponses
    0.77
    WithIOException
    0.77
    новништво
    0.75
     متعلقه
    0.75
    complexContent
    0.74
    Activations Density 1.046%

    No Known Activations