© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2091
    Prev
    Next
    INDEX
    Explanations

    sequences of mathematical or scientific symbols and terminology, especially formulas and quantities in a technical document.

    oai_token-act-pair · gemini-2.0-flash

    Scientific formulations

    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
     Formula
    -2.11
    Formula
    -2.11
     formulas
    -2.08
     formula
    -2.03
     formulae
    -1.94
     Formulas
    -1.92
    formula
    -1.89
     FORMULA
    -1.88
     Formulation
    -1.65
     formule
    -1.64
    POSITIVE LOGITS
     Context
    0.51
     désolés
    0.51
     '\\;'
    0.50
    TagMode
    0.50
    modb
    0.48
    AndroidJUnit
    0.47
    findpost
    0.47
     GenerationType
    0.46
    uxxxx
    0.46
    Context
    0.46
    Activations Density 3.550%

    No Known Activations