© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3500
    Prev
    Next
    INDEX
    Explanations

    words that create a peaceful or historical ambience

    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
    PageIndex
    -0.42
     Mid
    -0.40
     mid
    -0.39
     d
    -0.37
    leetcode
    -0.36
     merit
    -0.35
     hor
    -0.34
     l
    -0.34
    рованной
    -0.33
     ar
    -0.33
    POSITIVE LOGITS
    RenderAtEndOf
    1.07
     فريبيس
    0.95
     estekak
    0.92
    IntoConstraints
    0.89
    OGND
    0.88
    MENAFN
    0.87
     للمعارف
    0.84
    DockStyle
    0.82
    Sucesor
    0.82
     onCancelled
    0.82
    Activations Density 13.944%

    No Known Activations