© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8219
    Prev
    Next
    INDEX
    Explanations

    a dog named Spike engaging in sexual activity

    oai_token-act-pair · gemini-2.0-flash

    licking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ртка
    -0.49
     odc
    -0.48
    cepteur
    -0.48
     piele
    -0.47
     groomed
    -0.47
     neutrophils
    -0.47
     tối
    -0.47
    ClientRect
    -0.46
    ähren
    -0.46
    PageFactory
    -0.46
    POSITIVE LOGITS
     незавершена
    0.95
    IsMutable
    0.90
    MigrationBuilder
    0.83
    extAlignment
    0.79
    SourceChecksum
    0.77
    AddTagHelper
    0.76
    NameInMap
    0.71
     متعلقه
    0.70
    ]")]
    0.68
    webElementXpaths
    0.67
    Activations Density 2.709%

    No Known Activations