© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13908
    Prev
    Next
    INDEX
    Explanations

    the word "record" preceded by "the", along with a few other "the" phrases

    oai_token-act-pair · gemini-2.0-flash

    the record

    np_max-act · gemini-2.0-flash

    the

    np_max-act-logits · gpt-5-mini
    Triggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    SourceChecksum
    -0.61
     ExecuteAsync
    -0.59
     TestBed
    -0.57
     jadx
    -0.55
    Véxase
    -0.54
    toByteArray
    -0.53
     disambiguazione
    -0.53
    IContainer
    -0.50
    <bos>
    -0.50
    localVar
    -0.50
    POSITIVE LOGITS
     aéri
    0.69
    onthe
    0.67
    OnThe
    0.63
    ofire
    0.60
     on
    0.60
    RegressionTest
    0.59
     عليها
    0.54
    ölkerung
    0.54
     trên
    0.54
    setGeometry
    0.54
    Activations Density 0.261%

    No Known Activations