© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5131
    Prev
    Next
    INDEX
    Explanations

    words and phrases used in scientific articles, particularly those related to physics, including terminology, references, and mathematical expressions.

    oai_token-act-pair · gemini-2.0-flash

    physics/chemistry concepts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    AutoScaleMode
    -0.70
     ſtate
    -0.65
    GraphicsUnit
    -0.63
     تانيه
    -0.61
    abetes
    -0.60
    webElementXpaths
    -0.58
     Réponses
    -0.58
     purpoſe
    -0.58
    >//
    -0.57
     ©️
    -0.57
    POSITIVE LOGITS
     flown
    0.53
    SharedDtor
    0.52
    ziplin
    0.51
    ThemeOverlay
    0.50
     ::=
    0.50
    Пото
    0.49
    êté
    0.48
    Portale
    0.48
    ष्
    0.48
     pardoned
    0.48
    Activations Density 5.154%

    No Known Activations