© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8308
    Prev
    Next
    INDEX
    Explanations

    words in math papers that are often used together when studying various algebraic structures

    oai_token-act-pair · gemini-2.0-flash

    technical terms related to classification and algebra

    np_token-act-pair-logits · gpt-4o-mini

    scientific/mathematical text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     Unido
    -0.46
     BitmapFactory
    -0.44
    inheritDoc
    -0.43
    addPreferredGap
    -0.43
    imize
    -0.40
    turn
    -0.39
     Suzy
    -0.39
    AÇÃO
    -0.39
     CCS
    -0.39
    נג
    -0.39
    POSITIVE LOGITS
    ItemBackground
    0.81
     Normdatei
    0.77
    MIDDLEWARE
    0.68
    Personensuche
    0.68
    ViewFeatures
    0.64
    InjectAttribute
    0.60
    الإنجليزية
    0.60
    UnsafeEnabled
    0.60
    الحياه
    0.58
     متعلقه
    0.58
    Activations Density 1.232%

    No Known Activations