© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15719
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to medical symptoms, conditions, or health-related statistics.

    oai_token-act-pair · gemini-2.0-flash

    suffer

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     evolução
    -0.49
    kijken
    -0.47
     DataTypes
    -0.47
     Japão
    -0.44
    ясни
    -0.44
     calientes
    -0.41
     amarillas
    -0.41
     écout
    -0.41
     inconn
    -0.40
     utilização
    -0.40
    POSITIVE LOGITS
     suffer
    2.06
     suffers
    2.00
     suffering
    1.99
    suffering
    1.73
     Suffer
    1.73
     Suffering
    1.72
     suffered
    1.66
     sufre
    1.29
     sufferer
    1.27
     sufferings
    1.27
    Activations Density 3.334%

    No Known Activations