© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2942
    Prev
    Next
    INDEX
    Explanations

    text from scientific publications about physics, especially related to magnetism, spin, and related phenomena, frequently with mathematical notation.

    oai_token-act-pair · gemini-2.0-flash

    physics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     siè
    -0.59
    MethodManager
    -0.58
     natale
    -0.58
     enfans
    -0.58
     bershka
    -0.57
    PickerController
    -0.56
     définiti
    -0.55
     voul
    -0.55
     omnia
    -0.54
     electrónicos
    -0.53
    POSITIVE LOGITS
    ngrx
    0.67
    NameInMap
    0.59
     disambiguazione
    0.59
    دانشنامهٔ
    0.53
     Italijani
    0.51
    Diweddarwch
    0.50
     chi̍t
    0.50
    SharedCtor
    0.50
    |()
    0.50
    MemoryWarning
    0.49
    Activations Density 3.651%

    No Known Activations