© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2428
    Prev
    Next
    INDEX
    Explanations

    terms related to the origin and structure of the universe as well as the names and attributes of deities in a particular religion

    oai_token-act-pair · gemini-2.0-flash

    cosmology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    ToAction
    -0.49
     Jerome
    -0.49
    AlterField
    -0.46
    colta
    -0.45
    leno
    -0.45
     eens
    -0.44
     aer
    -0.43
    orme
    -0.43
    ürzen
    -0.42
     Gregory
    -0.42
    POSITIVE LOGITS
     multiverse
    0.64
    icoot
    0.63
     universe
    0.60
    :✨
    0.59
     universes
    0.59
    Kaynakça
    0.58
     Administrativna
    0.58
     宇宙
    0.57
    Xna
    0.56
     domande
    0.56
    Activations Density 1.453%

    No Known Activations