© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3266
    Prev
    Next
    INDEX
    Explanations

    passages discussing binary code, probabilities, or coin flips.

    oai_token-act-pair · gemini-2.0-flash

    Quantum computing and probabilities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     يتيمه
    -0.57
    ()")
    -0.57
     =>
    -0.52
    Skład
    -0.52
    InputBorder
    -0.50
    haa
    -0.50
    itanie
    -0.50
    thanes
    -0.49
     Modus
    -0.49
    forth
    -0.49
    POSITIVE LOGITS
    Geplaatst
    0.69
    onViewCreated
    0.65
     zeroes
    0.60
    coccus
    0.57
     الدولى
    0.57
     forbindelse
    0.55
    FailureListener
    0.55
    раздо
    0.54
     zero
    0.54
    WindowConstants
    0.54
    Activations Density 1.205%

    No Known Activations