© 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. 15748
    Prev
    Next
    INDEX
    Explanations

    relationships between events, people, or things, within a defined time span, as often found in scientific studies of medical treatments.

    oai_token-act-pair · gemini-2.0-flash

    Medical study context

    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
    bootstrapcdn
    -0.83
     actionTypes
    -0.70
     protoimpl
    -0.69
     professionali
    -0.65
    }))
    -0.64
     conservé
    -0.63
    MethodManager
    -0.62
    AsUp
    -0.60
    Története
    -0.58
    oredCriteria
    -0.58
    POSITIVE LOGITS
     full
    0.49
     khi
    0.48
    ole
    0.44
     passing
    0.42
     admission
    0.42
     when
    0.41
    ilog
    0.40
    mailed
    0.39
     Full
    0.39
    cosal
    0.39
    Activations Density 6.408%

    No Known Activations