© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7876
    Prev
    Next
    INDEX
    Explanations

    the character sequence "ol...de" and some other seemingly unrelated character sequences

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    orteur
    -0.79
     FetchType
    -0.77
    esgue
    -0.75
    FieldBuilder
    -0.72
    بوابة
    -0.64
     صوتيه
    -0.64
    ureusement
    -0.62
    ubehör
    -0.62
    mmate
    -0.61
     Picchu
    -0.61
    POSITIVE LOGITS
     old
    1.80
    Old
    1.56
    old
    1.51
     OLD
    1.49
     Old
    1.48
     older
    1.48
     vieux
    1.38
     age
    1.35
     viejo
    1.30
    Older
    1.30
    Activations Density 0.298%

    No Known Activations