© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13327
    Prev
    Next
    INDEX
    Explanations

    concepts and terminology used in politics, medicine, technology/media, and relationships

    oai_token-act-pair · gemini-2.0-flash

    Abstract concepts and issues

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    have
    -0.47
    system
    -0.45
    are
    -0.41
     system
    -0.38
     have
    -0.35
    ;
    -0.34
    ứng
    -0.30
    ystem
    -0.30
    Referanser
    -0.29
    ärs
    -0.29
    POSITIVE LOGITS
    ValueStyle
    1.13
    UnusedPrivate
    0.98
    RegistryLite
    0.96
    ReusableCell
    0.96
    SerializedSize
    0.94
    SourceChecksum
    0.93
    :✨
    0.93
    elemField
    0.91
     doInBackground
    0.90
    invokeLater
    0.86
    Activations Density 10.380%

    No Known Activations