© 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. 5064
    Prev
    Next
    INDEX
    Explanations

    words related to exercise and physical activity, often following a person's preferences

    oai_token-act-pair · gemini-2.0-flash

    class

    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
     CreateTagHelper
    -0.67
     fubject
    -0.60
    EditorBrowsable
    -0.58
     Majefty
    -0.58
    SafeMath
    -0.57
     Efq
    -0.57
     forKey
    -0.56
     ſche
    -0.56
    %
    -0.55
    municipi
    -0.55
    POSITIVE LOGITS
     class
    1.05
     Class
    1.02
     classes
    0.96
     Classes
    0.94
    Class
    0.93
    Classes
    0.83
    class
    0.83
     classe
    0.74
     CLASSES
    0.74
     clase
    0.71
    Activations Density 1.077%

    No Known Activations