© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2457
    Prev
    Next
    INDEX
    Explanations

    code snippets and associated jargon

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    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
    ########.
    -0.73
     fading
    -0.63
    
    -0.62
    .*")]
    -0.61
    PerformLayout
    -0.60
     مرئيه
    -0.59
     deactivated
    -0.59
     שוליים
    -0.59
     violated
    -0.58
     faded
    -0.58
    POSITIVE LOGITS
    ConstraintMaker
    0.69
    sstelle
    0.61
    HasAnnotation
    0.50
    MessageTagHelper
    0.48
     gesteld
    0.48
    Там
    0.47
     وتسجيلات
    0.46
     Elin
    0.45
     gevolg
    0.45
    (')
    0.44
    Activations Density 2.629%

    No Known Activations