© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6560
    Prev
    Next
    INDEX
    Explanations

    the word "peak" when describing data.

    oai_token-act-pair · gemini-2.0-flash

    peak

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     '\\;'
    -0.72
    BASEPATH
    -0.59
     @"/
    -0.59
    TagMode
    -0.57
    OrWhiteSpace
    -0.54
     الدولى
    -0.53
     getItemCount
    -0.52
     cytok
    -0.51
    mybatisplus
    -0.50
     rainbows
    -0.50
    POSITIVE LOGITS
    :✨
    0.62
    styleType
    0.54
    bran
    0.50
     jadx
    0.49
    InSection
    0.49
     odd
    0.49
     JScrollPane
    0.48
    +:+
    0.47
     SER
    0.47
    Odd
    0.46
    Activations Density 1.263%

    No Known Activations