© 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. 3618
    Prev
    Next
    INDEX
    Explanations

    the letter 't', and also some common contractions like "Cos", "Sup", "stead", and "Ri"

    oai_token-act-pair · gemini-2.0-flash

    t

    np_max-act · 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
     myſelf
    -0.79
     Diſ
    -0.76
     Reſ
    -0.73
     himſelf
    -0.71
     Cæsar
    -0.69
     Monfieur
    -0.69
     Eſ
    -0.69
     reaſon
    -0.68
     Majefty
    -0.68
     poffible
    -0.68
    POSITIVE LOGITS
     للاسماء
    0.70
    ArrowToggle
    0.62
    oa̍t
    0.54
    Хьажоргаш
    0.52
    Nationalité
    0.50
    Extinguishing
    0.48
     diplôme
    0.47
     DRO
    0.47
    กัน
    0.47
    minster
    0.46
    Activations Density 1.032%

    No Known Activations