© 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. 4767
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to computer or device features and functions

    oai_token-act-pair · gemini-2.0-flash

    function or feature

    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
    žu
    -0.45
     جات
    -0.44
    CRITICAL
    -0.37
    reon
    -0.36
    yta
    -0.36
    Bench
    -0.35
    ario
    -0.35
     hợp
    -0.35
     dolu
    -0.35
     thừa
    -0.35
    POSITIVE LOGITS
     function
    2.11
     feature
    2.08
     functionality
    1.94
    function
    1.82
     Function
    1.81
     Feature
    1.80
    功能
    1.79
    feature
    1.78
     functions
    1.73
     기능
    1.68
    Activations Density 3.072%

    No Known Activations