© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6264
    Prev
    Next
    INDEX
    Explanations

    words related to eye surgery and ophthalmology, in particular the cutting out of the lens to treat cateracts

    oai_token-act-pair · gemini-2.0-flash

    Eye-related contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    TypedDataSet
    -0.53
    massen
    -0.53
     quim
    -0.52
    UPAC
    -0.51
     FetchType
    -0.50
    SceneManagement
    -0.50
     McQu
    -0.50
    CBM
    -0.49
     facial
    -0.48
    Zin
    -0.47
    POSITIVE LOGITS
    featureID
    0.77
     المعيارى
    0.60
    XmlAccessType
    0.59
     esternos
    0.59
     AssemblyProduct
    0.59
    protoimpl
    0.57
     Normdatei
    0.57
    DeleteBehavior
    0.57
    Jeografia
    0.55
    oredCriteria
    0.55
    Activations Density 2.111%

    No Known Activations