© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14613
    Prev
    Next
    INDEX
    Explanations

    instances of technical vocabulary, likely related to scientific or engineering fields

    oai_token-act-pair · gemini-2.0-flash

    -tion words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     nôtre
    -0.56
     odkazy
    -0.54
     సౌకర్య
    -0.54
     بيها
    -0.54
     oprot
    -0.52
    >>()
    -0.52
    énieurs
    -0.51
     ModelExpression
    -0.51
     تكبرها
    -0.50
    ILayout
    -0.49
    POSITIVE LOGITS
     evaluation
    1.09
     deployment
    1.01
     acquisition
    1.00
     submission
    0.98
     removal
    0.98
     release
    0.93
     conversion
    0.93
     integration
    0.93
     adaptation
    0.92
     installation
    0.91
    Activations Density 7.848%

    No Known Activations