© 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. 12220
    Prev
    Next
    INDEX
    Explanations

    words that denote proof and generalization in the context of mathematical equations

    oai_token-act-pair · gemini-2.0-flash

    mathematical derivations

    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
     يتيمه
    -0.84
    MLLoader
    -0.79
    styleType
    -0.66
    DockStyle
    -0.65
    kháu
    -0.63
     Chwiliwch
    -0.62
    ViewFeatures
    -0.62
     esternos
    -0.60
    jewództ
    -0.60
     disponibilités
    -0.60
    POSITIVE LOGITS
    ưỡi
    0.55
     espagne
    0.55
     specchio
    0.52
    [](
    0.50
    echt
    0.50
    Posted
    0.50
     marge
    0.50
     mises
    0.48
     addSubview
    0.47
    onViewCreated
    0.46
    Activations Density 8.382%

    No Known Activations