© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12500
    Prev
    Next
    INDEX
    Explanations

    adverbs and adjectives that express infrequency or insignificance, as well as words closely related to quantity or amount

    oai_token-act-pair · gemini-2.0-flash

    infrequency

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     AssemblyCulture
    -0.88
     незавершена
    -0.82
    MessageTagHelper
    -0.81
    MigrationBuilder
    -0.79
     ivelany
    -0.75
    ContentAsync
    -0.74
    Datuak
    -0.74
    SequentialGroup
    -0.73
     resourceCulture
    -0.71
     utafitiHapana
    -0.70
    POSITIVE LOGITS
     rare
    0.77
    rare
    0.67
     Rare
    0.66
    Rare
    0.65
     RARE
    0.62
     limited
    0.61
     infrequent
    0.59
    少数
    0.59
    罕
    0.57
     Limited
    0.57
    Activations Density 1.499%

    No Known Activations