© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 9001
    Prev
    Next
    INDEX
    Explanations

    words describing parts and features of mechanical objects

    oai_token-act-pair · gemini-2.0-flash

    mechanical parts

    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
     BorderRadius
    -0.90
    SequentialGroup
    -0.80
     Hotspur
    -0.69
     незавершена
    -0.68
    bootstrapcdn
    -0.67
     EdgeInsets
    -0.65
    httphttps
    -0.64
     الرياضيه
    -0.63
    tagHelperRunner
    -0.62
    OrWhiteSpace
    -0.62
    POSITIVE LOGITS
    
    0.59
    InitVars
    0.50
     holding
    0.47
    queryInterface
    0.47
     top
    0.46
     hvert
    0.46
     dimension
    0.45
     carrying
    0.43
     below
    0.43
     on
    0.43
    Activations Density 3.178%

    No Known Activations