© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10071
    Prev
    Next
    INDEX
    Explanations

    phrases and constructions for comparing values or levels

    oai_token-act-pair · gemini-2.0-flash

    relative quantity/measurement

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     unut
    -0.63
    TryParse
    -0.59
     revés
    -0.57
    Mutual
    -0.55
     antennae
    -0.55
    detail
    -0.54
    Detail
    -0.54
    nanoTime
    -0.53
     Detail
    -0.52
     colpa
    -0.52
    POSITIVE LOGITS
     дописавши
    0.80
     propOrder
    0.77
    AccessorTable
    0.71
    cshtml
    0.54
     насељу
    0.53
     that
    0.53
     the
    0.51
     disambiguazione
    0.50
     or
    0.49
     <",
    0.49
    Activations Density 4.885%

    No Known Activations