© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10949
    Prev
    Next
    INDEX
    Explanations

    the words "patch" and "accident", and is potentially related to software updates or car crashes

    oai_token-act-pair · gemini-2.0-flash

    programming patches and accidents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     accident
    -1.04
    <bos>
    -0.94
    Accident
    -0.94
    accident
    -0.88
     Accident
    -0.82
     ACCIDENT
    -0.73
     patch
    -0.71
    PATCH
    -0.69
     patches
    -0.68
    patch
    -0.65
    POSITIVE LOGITS
     pinulongan
    0.71
    SizeMode
    0.66
     متعلقه
    0.64
    jmniej
    0.63
    
    0.62
    AAT
    0.59
    ReusableCell
    0.57
     viewDidLoad
    0.54
    ConverterFactory
    0.54
     ddelweddau
    0.54
    Activations Density 0.881%

    No Known Activations