© 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. 13554
    Prev
    Next
    INDEX
    Explanations

    words and phrases that are in all caps or are very important to the context of the document

    oai_token-act-pair · 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
    awtextra
    -0.88
     CreateTagHelper
    -0.81
    
    -0.77
    ⓧ
    -0.72
    InjectAttribute
    -0.70
    WriteAttribute
    -0.69
     EconPapers
    -0.67
    MessageTagHelper
    -0.66
    الحياه
    -0.66
    AndEndTag
    -0.66
    POSITIVE LOGITS
     falls
    0.80
     is
    0.79
     falling
    0.69
     fall
    0.68
     Falling
    0.65
    Falling
    0.60
     Fall
    0.60
     fell
    0.58
     first
    0.57
     can
    0.57
    Activations Density 5.864%

    No Known Activations