© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1808
    Prev
    Next
    INDEX
    Explanations

    mentions of the first-person pronoun in different languages.

    oai_token-act-pair · gemini-2.0-flash

    terms related to programming and technical documentation

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

    ي

    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
    Negative Logits
    x
    -0.51
    xd
    -0.46
     gainera
    -0.43
    xf
    -0.41
     authors
    -0.40
    Più
    -0.40
    MathML
    -0.40
     defaultstate
    -0.40
     Bahia
    -0.39
     ties
    -0.38
    POSITIVE LOGITS
     EconPapers
    0.88
    Autoritní
    0.77
    WithIOException
    0.74
    PyExc
    0.66
     autorytatywna
    0.65
    assertRaises
    0.60
     disambiguazione
    0.59
    AutoScaleMode
    0.59
     AssemblyCulture
    0.58
    setupUi
    0.58
    Activations Density 0.993%

    No Known Activations