© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2514
    Prev
    Next
    INDEX
    Explanations

    words and phrases that identify a moment of change or discovery

    oai_token-act-pair · gemini-2.0-flash

    "occur"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     poveznice
    -0.58
    bihan
    -0.47
    Standing
    -0.47
    brtc
    -0.45
    +][
    -0.44
     Anas
    -0.43
    かした
    -0.42
    ровна
    -0.42
    netes
    -0.42
     onCancelled
    -0.42
    POSITIVE LOGITS
     occurs
    1.59
     occurred
    1.54
     occur
    1.54
     happened
    1.36
    occur
    1.33
     happens
    1.30
    occurs
    1.28
     happen
    1.27
     Occur
    1.24
     occured
    1.21
    Activations Density 2.911%

    No Known Activations