© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9999
    Prev
    Next
    INDEX
    Explanations

    words involved in scientific and technological documents, including government, finance and collaboration

    oai_token-act-pair · gemini-2.0-flash

    private

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     SafeMath
    -0.63
    IsContent
    -0.56
     العنوان
    -0.54
    vernote
    -0.53
    ktop
    -0.51
    CppCodeGen
    -0.48
    |()
    -0.48
    mtrl
    -0.47
     (°
    -0.46
    rawDesc
    -0.45
    POSITIVE LOGITS
     private
    3.02
     Private
    2.47
    private
    2.44
    Private
    2.42
     PRIVATE
    2.39
     privada
    2.13
     privately
    2.11
    PRIVATE
    2.03
     privado
    2.00
     privados
    1.98
    Activations Density 4.947%

    No Known Activations