© 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. 16349
    Prev
    Next
    INDEX
    Explanations

    a mix of cuisine terms and seemingly unrelated words, possibly due to shared prefixes or suffixes

    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
     propOrder
    -0.59
    lė
    -0.54
    uoš
    -0.52
    jfree
    -0.50
    itions
    -0.49
    ophanes
    -0.48
    ticularly
    -0.48
     oignons
    -0.48
    ingway
    -0.47
    iesis
    -0.47
    POSITIVE LOGITS
     utafitiHapana
    0.57
     }}"></
    0.57
    ReusableCell
    0.55
    RenderAtEndOf
    0.52
    彿
    0.50
     arras
    0.49
     للمعارف
    0.47
     Kais
    0.46
     Macle
    0.46
    parms
    0.45
    Activations Density 0.088%

    No Known Activations