© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1374
    Prev
    Next
    INDEX
    Explanations

    mathematical and physics equations and notation, particularly fractions, integrals, sums, and symbols like Greek letters

    oai_token-act-pair · gemini-2.0-flash

    {

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     domestique
    -0.46
     I
    -0.41
     colonie
    -0.41
    programa
    -0.40
     ő
    -0.40
     domestiques
    -0.40
     individuale
    -0.38
     собі
    -0.38
     Portuguesa
    -0.38
     Argentino
    -0.37
    POSITIVE LOGITS
    RenderAtEndOf
    1.09
    ])));
    1.05
    +#+#
    1.02
    ScopeManager
    0.99
     })
    0.94
     ***!
    0.93
     tartalomajánló
    0.93
    LookAnd
    0.89
     مشين
    0.87
    ChildScrollView
    0.87
    Activations Density 13.692%

    No Known Activations