© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11997
    Prev
    Next
    INDEX
    Explanations

    code snippets including links, values, and methods related to tuples or objects

    oai_token-act-pair · gemini-2.0-flash

    computer code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    typeorm
    -0.74
    ]=>
    -0.62
     pymongo
    -0.59
    Embeddable
    -0.57
    ssohn
    -0.56
     Мексичка
    -0.54
    atività
    -0.53
    SpringBootTest
    -0.52
    DockStyle
    -0.52
    jooq
    -0.52
    POSITIVE LOGITS
    CppMethod
    0.91
     <<<<<<<<<<<<<<
    0.87
     autorytatywna
    0.81
     localObject
    0.78
     becauſe
    0.76
    :✨
    0.72
    bibfield
    0.71
     (;;
    0.69
    NullCheck
    0.66
    bibinfo
    0.64
    Activations Density 1.636%

    No Known Activations