© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14137
    Prev
    Next
    INDEX
    Explanations

    words or phrases that either indicate a question, a unique feature, or something that is really good

    oai_token-act-pair · gemini-2.0-flash

    set

    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
     jadx
    -0.67
     NSCoder
    -0.58
    thâu
    -0.57
      (
    -0.57
     الحره
    -0.56
    URLException
    -0.54
    HtmlAttribute
    -0.54
    fireEvent
    -0.54
    __(/*!
    -0.53
     onAnimation
    -0.52
    POSITIVE LOGITS
     set
    2.33
     sets
    2.19
     Set
    2.05
    set
    1.99
    Set
    1.90
     Sets
    1.87
     SET
    1.75
     setting
    1.73
    Sets
    1.68
    sets
    1.67
    Activations Density 2.238%

    No Known Activations