© 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. 8111
    Prev
    Next
    INDEX
    Explanations

    the word "seal" and related terms.

    oai_token-act-pair · gemini-2.0-flash

    seal

    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
    1
    -0.74
    2
    -0.70
    ه
    -0.69
    8
    -0.66
    3
    -0.66
    en
    -0.65
    4
    -0.63
    er
    -0.63
    6
    -0.61
    0
    -0.60
    POSITIVE LOGITS
    RegressionTest
    1.30
    TagMode
    1.24
     дописавши
    1.17
    sizeCache
    1.07
    IntoConstraints
    1.05
    UnknownFields
    1.03
     propOrder
    1.01
    
    1.00
    )");
    1.00
    delwed
    0.99
    Activations Density 0.610%

    No Known Activations