© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11511
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially related to database models and object-relational mapping (ORM)

    oai_token-act-pair · gemini-2.0-flash

    ORM and models

    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
    zewod
    -0.45
    Sin
    -0.43
     Industri
    -0.41
     morrow
    -0.41
     trợ
    -0.40
    РС
    -0.39
     hoàn
    -0.39
    桿
    -0.37
     adjuvant
    -0.37
    spot
    -0.37
    POSITIVE LOGITS
    TypedDataSet
    1.19
     autorytatywna
    1.16
     EconPapers
    1.12
    mybatisplus
    1.10
    addCriterion
    1.06
    typeorm
    1.06
    migrationBuilder
    1.04
    Personendaten
    0.97
    Eloquent
    0.97
    DataAnnotations
    0.95
    Activations Density 1.179%

    No Known Activations