© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9451
    Prev
    Next
    INDEX
    Explanations

    equation syntax or the phrase "as [pronoun] [form of 'to be']"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     useEffect
    -0.61
    InstrumentedTest
    -0.58
     ModelExpression
    -0.56
     otomatig
    -0.56
    raci
    -0.54
     Exactos
    -0.52
    moveToFirst
    -0.52
     kasarigan
    -0.50
    prefixer
    -0.48
     intptr
    -0.47
    POSITIVE LOGITS
    AddHtmlAttribute
    0.58
     Tanjung
    0.51
    issau
    0.51
    VersionUID
    0.50
    zhen
    0.49
    время
    0.49
    shafen
    0.48
     Mankind
    0.47
    kloped
    0.47
    lactin
    0.47
    Activations Density 0.328%

    No Known Activations