© 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. 5007
    Prev
    Next
    INDEX
    Explanations

    a diverse set of words that connect clauses and add meaning, including prepositions, conjunctions, and degree words.

    oai_token-act-pair · gemini-2.0-flash

    the pronoun 'it'

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

    it

    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
     shes
    -0.87
     They
    -0.81
     him
    -0.81
     she
    -0.77
    They
    -0.77
     they
    -0.76
    DoubleQuotes
    -0.69
     them
    -0.68
    彼らは
    -0.66
     họ
    -0.66
    POSITIVE LOGITS
     it
    2.56
    It
    1.66
     It
    1.57
    it
    1.45
    มัน
    0.97
     آن
    0.82
    それは
    0.77
     nó
    0.74
     ello
    0.74
     यह
    0.72
    Activations Density 6.014%

    No Known Activations