© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15700
    Prev
    Next
    INDEX
    Explanations

    words related to magnetic fields and motors

    oai_token-act-pair · gemini-2.0-flash

    magnetism

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     TestBed
    -0.55
     ErrIntOverflow
    -0.52
    addCriterion
    -0.49
    StoryboardSegue
    -0.48
    Ƚ
    -0.45
     présidenti
    -0.44
     knex
    -0.42
    באנגלית
    -0.42
    Fprintf
    -0.41
    AndFlush
    -0.41
    POSITIVE LOGITS
     magnet
    1.09
    magnet
    0.98
     magnets
    0.98
     magnetic
    0.96
     Magnet
    0.92
     magne
    0.92
     magnetism
    0.92
    magne
    0.91
     Magne
    0.91
    Magnet
    0.89
    Activations Density 2.115%

    No Known Activations