© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6979
    Prev
    Next
    INDEX
    Explanations

    information about a specific person getting an education from Hungarian, British, or American universities

    oai_token-act-pair · gemini-2.0-flash

    academic/research context

    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
     quick
    -0.52
    クイ
    -0.48
    engesch
    -0.47
     Spread
    -0.47
    edah
    -0.46
    چه
    -0.44
     vanno
    -0.44
     spread
    -0.43
    allinen
    -0.43
     Sahib
    -0.43
    POSITIVE LOGITS
    Демографія
    0.79
    endphp
    0.77
    +#+#
    0.76
     CWE
    0.75
    Parcelize
    0.73
    Попис
    0.73
     GenerationType
    0.70
    MemoryWarning
    0.68
    CloseOperation
    0.63
    ValueStyle
    0.63
    Activations Density 0.208%

    No Known Activations