© 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. 11533
    Prev
    Next
    INDEX
    Explanations

    words related to conflict or regulation by authorities

    oai_token-act-pair · gemini-2.0-flash

    named entities/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_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
    lager
    -0.49
    벌
    -0.39
     aján
    -0.37
    لیس
    -0.36
     oficina
    -0.35
     ar
    -0.35
    ลัง
    -0.35
     mostró
    -0.34
     fior
    -0.34
     legales
    -0.34
    POSITIVE LOGITS
    AndEndTag
    1.16
    
    0.92
    Personendaten
    0.90
    DockStyle
    0.88
    IContainer
    0.87
    Билгалдахарш
    0.81
     дописавши
    0.81
    matchCondition
    0.79
     الرياضيه
    0.79
    principalTable
    0.78
    Activations Density 2.348%

    No Known Activations