© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12468
    Prev
    Next
    INDEX
    Explanations

    terms related to physics and math formulas and their results

    oai_token-act-pair · gemini-2.0-flash

    efficiency

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     getApplication
    -0.54
     Daß
    -0.52
    "";
    -0.52
     getElement
    -0.51
     kartą
    -0.50
    ради
    -0.50
    WING
    -0.50
    __(/*!
    -0.49
     للاسماء
    -0.49
    ENIX
    -0.48
    POSITIVE LOGITS
    <bos>
    0.63
     InputDecoration
    0.55
    stdafx
    0.51
    AnimationsModule
    0.50
     level
    0.50
    Демографія
    0.49
     getItemId
    0.49
    djangoproject
    0.47
    FFIX
    0.46
     المعرف
    0.46
    Activations Density 4.063%

    No Known Activations