© 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. 12807
    Prev
    Next
    INDEX
    Explanations

    words that express a business-like appeal to a targeted demographic

    oai_token-act-pair · gemini-2.0-flash

    society and trends

    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
     gynhyrchwyd
    -0.81
     autorytatywna
    -0.74
    reportWebVitals
    -0.68
     oprot
    -0.66
     незавершена
    -0.66
    ^(@)
    -0.64
     Jefus
    -0.64
    脚注の使い方
    -0.63
    хьтан
    -0.63
    PerformLayout
    -0.59
    POSITIVE LOGITS
     digital
    0.59
     ever
    0.55
     Digital
    0.53
    IsContent
    0.50
     new
    0.50
     nouveau
    0.50
    เดิม
    0.49
     Ten
    0.47
     AppComponent
    0.47
     digitally
    0.47
    Activations Density 2.357%

    No Known Activations