© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4034
    Prev
    Next
    INDEX
    Explanations

    passages about breast implants or cancer

    oai_token-act-pair · gemini-2.0-flash

    breast

    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
    Not in Any Lists

    No Comments

    Negative Logits
    awtextra
    -0.78
    κτηρισ
    -0.74
     EdgeInsets
    -0.65
    Portail
    -0.62
    Viki
    -0.61
    <bos>
    -0.60
     насељу
    -0.60
     disambiguazione
    -0.58
    ">//
    -0.58
    quelize
    -0.57
    POSITIVE LOGITS
     NUKAT
    0.50
    τεί
    0.42
    AlterField
    0.40
     incomplète
    0.36
     probe
    0.35
     lenker
    0.35
    änä
    0.35
    ագրություններ
    0.34
    XmlAccessType
    0.34
    Erstellt
    0.34
    Activations Density 1.547%

    No Known Activations