© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 462
    Prev
    Next
    INDEX
    Explanations

    the string "Ver" followed by other letters or "tice"

    oai_token-act-pair · gemini-2.0-flash

    Ver

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Ver
    -2.06
     ver
    -2.03
    ver
    -1.91
     Ver
    -1.87
     VER
    -1.70
    VER
    -1.66
    vers
    -1.17
    veri
    -1.03
     Verm
    -1.00
     Verk
    -0.96
    POSITIVE LOGITS
     sẻ
    0.59
     препратки
    0.56
    Beijinhos
    0.56
    RRect
    0.55
    NameInMap
    0.54
     Gegenstand
    0.52
    ADVERTISEMENT
    0.52
    ImageContext
    0.52
    ناصر
    0.50
     constant
    0.49
    Activations Density 6.486%

    No Known Activations