© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11947
    Prev
    Next
    INDEX
    Explanations

    a variety of math, code, or specialized symbols/notations.

    oai_token-act-pair · gemini-2.0-flash

    numbers and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     autorytatywna
    -0.65
    出版年
    -0.59
     Raad
    -0.58
    retario
    -0.51
    disposing
    -0.51
     virtual
    -0.50
     oxidase
    -0.50
    มาะ
    -0.48
    WireFormat
    -0.48
    oxidase
    -0.48
    POSITIVE LOGITS
     protoimpl
    0.70
     الرياضيه
    0.65
     unknownFields
    0.64
    :✨
    0.63
     puissiez
    0.60
     mostrarán
    0.59
    ніципа
    0.57
     nonatomic
    0.57
     utilice
    0.56
     nôtre
    0.56
    Activations Density 25.752%

    No Known Activations