© 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. 9698
    Prev
    Next
    INDEX
    Explanations

    variations of "have" and some uncommon words starting with "ass" that are adjacent to capital letters

    oai_token-act-pair · gemini-2.0-flash

    d

    np_max-act · gemini-2.0-flash
    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
    ΗΣ
    -0.52
     poursuite
    -0.52
     richesse
    -0.50
     XCTest
    -0.50
     BIBSYS
    -0.50
     COMERC
    -0.49
     digitais
    -0.49
     برانيه
    -0.49
    ‌لار
    -0.49
     licorne
    -0.48
    POSITIVE LOGITS
     has
    1.27
     have
    1.24
     had
    1.20
     HAS
    1.20
    Has
    1.16
     HAVE
    1.16
     Has
    1.15
     Have
    1.13
    Have
    1.10
    have
    1.05
    Activations Density 0.280%

    No Known Activations