© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15777
    Prev
    Next
    INDEX
    Explanations

    content related to legal and political actions, like treaties, rights, and ethical bodies

    oai_token-act-pair · gemini-2.0-flash

    Legal and political situations

    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
    EndGlobalSection
    -0.91
     للاسماء
    -0.89
    rungsseite
    -0.84
     pinulongan
    -0.83
    __':
    -0.83
    Personensuche
    -0.81
     initComponents
    -0.80
    Obrázky
    -0.78
    AddHtmlAttribute
    -0.75
    Билгалдахарш
    -0.75
    POSITIVE LOGITS
    gggg
    0.44
     data
    0.41
    mentaire
    0.40
    材
    0.40
     light
    0.38
    executeQuery
    0.37
    ulls
    0.37
    storage
    0.37
     content
    0.37
     dati
    0.36
    Activations Density 3.336%

    No Known Activations