© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10861
    Prev
    Next
    INDEX
    Explanations

    the word "a" or "in" followed by other words.

    oai_token-act-pair · gemini-2.0-flash

    the word 'way'

    np_token-act-pair-logits · gpt-4o-mini

    a

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    脚注の使い方
    -0.65
    enumi
    -0.64
    Filmographie
    -0.58
    mogat
    -0.58
    Ecotoxicity
    -0.54
     通販
    -0.52
    jenige
    -0.52
    usermodel
    -0.52
     Leviathan
    -0.51
    /**
    -0.51
    POSITIVE LOGITS
     way
    1.09
    way
    0.86
    WAY
    0.84
     WAY
    0.81
     Way
    0.77
     ways
    0.76
    Way
    0.73
     manner
    0.66
     Manner
    0.62
    ways
    0.59
    Activations Density 1.634%

    No Known Activations