© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14334
    Prev
    Next
    INDEX
    Explanations

    words that appear in descriptions of hardware components and construction

    oai_token-act-pair · gemini-2.0-flash

    technical terms related to machinery or engineering

    np_token-act-pair-logits · gpt-4o-mini

    Structures

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    AutoScale
    -0.62
    PerformLayout
    -0.59
     indisponible
    -0.57
     LoggerFactory
    -0.57
    WillAppear
    -0.54
    WaitGroup
    -0.53
    addPreferredGap
    -0.52
     merito
    -0.50
    IsInitialized
    -0.50
    FXML
    -0.49
    POSITIVE LOGITS
    crollView
    0.56
     otomatig
    0.52
     flight
    0.52
    ESTR
    0.51
     chains
    0.51
    Kategori
    0.51
     AttributeSet
    0.50
     Bearing
    0.50
     tendons
    0.49
    Bearing
    0.49
    Activations Density 0.896%

    No Known Activations