© 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. 14749
    Prev
    Next
    INDEX
    Explanations

    colons, semicolons, open parenthesis, equal signs and the word "true" inside of code

    oai_token-act-pair · gemini-2.0-flash

    true/false assignment

    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
    Personendaten
    -0.90
    WebVitals
    -0.88
    astify
    -0.80
    RenderAtEndOf
    -0.80
    
    -0.77
     ویکی‌پدی
    -0.77
     للاسماء
    -0.77
    LookAnd
    -0.76
    DockStyle
    -0.75
    ValueStyle
    -0.73
    POSITIVE LOGITS
     TW
    0.60
     !
    0.59
     Tr
    0.55
     Tem
    0.53
     tem
    0.53
     tā
    0.52
     T
    0.51
    !
    0.49
     tr
    0.49
     !(
    0.49
    Activations Density 3.827%

    No Known Activations