© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12758
    Prev
    Next
    INDEX
    Explanations

    references to cancer and treatment

    oai_token-act-pair · gemini-2.0-flash

    cancer

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     PROCESSING
    -0.47
     Codes
    -0.47
     kaca
    -0.47
     William
    -0.47
    oris
    -0.46
     Code
    -0.45
     Skills
    -0.45
    isole
    -0.45
    médi
    -0.45
    odi
    -0.44
    POSITIVE LOGITS
     للاسماء
    0.74
    ftagPool
    0.71
     myſelf
    0.68
    جمعیت
    0.67
    MessageOf
    0.61
     purpoſe
    0.59
     uſe
    0.59
    XmlAccessorType
    0.58
     HasFactory
    0.58
    sizeCache
    0.57
    Activations Density 1.640%

    No Known Activations