© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 2758
    Prev
    Next
    INDEX
    Explanations

    astronomy or astrophysics terms related to the properties and evolution of stars

    oai_token-act-pair · gemini-2.0-flash

    scientific/astronomical texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    AndEndTag
    -0.79
    +#+#
    -0.68
    SizeMode
    -0.66
     récompenses
    -0.66
     CreateTagHelper
    -0.65
     '*':
    -0.62
    ientôt
    -0.62
     saco
    -0.61
     souten
    -0.61
    ículas
    -0.60
    POSITIVE LOGITS
     conn
    0.39
    calloc
    0.38
     band
    0.38
     bands
    0.38
     seal
    0.38
     Waterhouse
    0.37
    円で
    0.36
     sch
    0.35
     shark
    0.35
    setVerticalGroup
    0.35
    Activations Density 3.953%

    No Known Activations