© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13253
    Prev
    Next
    INDEX
    Explanations

    technical jargon related to law, consumer protection, and finance.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     primas
    -0.52
     Grove
    -0.48
    anxi
    -0.47
    cluse
    -0.47
    Grove
    -0.47
     Anexo
    -0.46
     rū
    -0.46
     parem
    -0.45
    wner
    -0.45
    큼
    -0.45
    POSITIVE LOGITS
    تقاوى
    1.30
    LookAnd
    1.23
    sizeCache
    1.17
    +:+
    1.15
    TypedDataSet
    1.14
    WithIOException
    1.12
     propOrder
    1.12
     protoimpl
    1.10
    UnsafeEnabled
    1.10
    IndentedString
    1.09
    Activations Density 50.935%

    No Known Activations