© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6430
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "edge" in different contexts

    oai_token-act-pair · gemini-2.0-flash

    edge

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     Majefty
    -1.48
     pleaſure
    -1.47
     itſelf
    -1.43
     myſelf
    -1.43
    ſelf
    -1.38
     purpoſe
    -1.33
     Efq
    -1.31
     Monfieur
    -1.29
     themſelves
    -1.28
     iſt
    -1.27
    POSITIVE LOGITS
     the
    0.66
     a
    0.57
     some
    0.57
     between
    0.56
    o
    0.56
     again
    0.55
     several
    0.54
    a
    0.53
     around
    0.52
    /
    0.52
    Activations Density 1.272%

    No Known Activations