© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11406
    Prev
    Next
    INDEX
    Explanations

    descriptions of a medical professional's education and work history

    oai_token-act-pair · gemini-2.0-flash

    Medical residency

    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
    исленность
    -0.44
     Pferd
    -0.43
    רד
    -0.41
    argento
    -0.41
     prá
    -0.40
    )][
    -0.39
     ']
    -0.38
    cdnjs
    -0.38
    打工
    -0.38
    ())))
    -0.38
    POSITIVE LOGITS
     Residents
    1.38
     residents
    1.31
    Residents
    1.26
     resident
    1.24
     Resident
    1.20
    Resident
    1.19
    residents
    1.17
     RESID
    1.10
    resident
    1.06
     residency
    1.02
    Activations Density 2.672%

    No Known Activations