© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15930
    Prev
    Next
    INDEX
    Explanations

    many common nouns and adjectives

    oai_token-act-pair · gemini-2.0-flash

    positioned

    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
     để
    -1.03
     щоб
    -1.02
     aby
    -0.95
     чтобы
    -0.93
     żeby
    -0.85
     כדי
    -0.79
     afin
    -0.75
     affinch
    -0.75
     чтоб
    -0.70
     nhằm
    -0.68
    POSITIVE LOGITS
    RenderAtEndOf
    0.78
    PerformLayout
    0.77
    abestanden
    0.69
    
    0.66
    SpringBootTest
    0.62
    stateProvider
    0.62
    ngdoc
    0.62
     resourceCulture
    0.62
     to
    0.60
     attirer
    0.59
    Activations Density 1.531%

    No Known Activations