© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15374
    Prev
    Next
    INDEX
    Explanations

    information about a person, specifically their name, profession, and artistic mediums

    oai_token-act-pair · gemini-2.0-flash

    art and artists

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    ]++;
    -0.60
    >[]
    -0.53
     enfance
    -0.51
     fulness
    -0.50
     aback
    -0.49
    ]--;
    -0.49
    ----</
    -0.49
     noastre
    -0.48
    ături
    -0.48
    ゴリー
    -0.47
    POSITIVE LOGITS
    findpost
    0.80
    tagHelperRunner
    0.78
    Билгалдахарш
    0.68
    onViewCreated
    0.65
    BeginContext
    0.62
    queryInterface
    0.60
     onCreateView
    0.59
     art
    0.57
    AndroidJUnit
    0.55
    Бахар
    0.55
    Activations Density 12.122%

    No Known Activations