© 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. 15112
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs (is, was, be, could, would) near intensifiers (very, most, easily) or quantifying terms/articles (a, an, the) and words implying potential utility/purpose.

    oai_token-act-pair · gemini-2.0-flash

    be

    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
     myſelf
    -1.71
     Efq
    -1.67
     Jefus
    -1.61
     للاسماء
    -1.48
     Monfieur
    -1.46
     uſed
    -1.45
     raiſ
    -1.44
     juſ
    -1.44
     poffible
    -1.44
     becauſe
    -1.43
    POSITIVE LOGITS
     
    0.43
     v
    0.36
     p
    0.35
     po
    0.34
    <eos>
    0.34
    \
    0.31
     \
    0.31
     of
    0.29
     de
    0.29
     [
    0.29
    Activations Density 6.556%

    No Known Activations