© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 576
    Prev
    Next
    INDEX
    Explanations

    the word "large" and words/phrases associated with size/scale/quantity

    oai_token-act-pair · gemini-2.0-flash

    large

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     large
    -2.02
    large
    -1.88
    Large
    -1.81
     Large
    -1.77
     LARGE
    -1.65
    LARGE
    -1.33
     largest
    -1.18
    larger
    -1.14
     larger
    -1.14
     huge
    -1.13
    POSITIVE LOGITS
    localctx
    0.73
    CodedInputStream
    0.66
    setVerticalGroup
    0.64
    ',
    0.59
     myſelf
    0.57
     purpoſe
    0.57
     PicClick
    0.56
    seamnă
    0.56
     faſt
    0.54
    )))),
    0.54
    Activations Density 3.585%

    No Known Activations