© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12389
    Prev
    Next
    INDEX
    Explanations

    the character sequence "ur" and "ul," often as parts of longer words

    oai_token-act-pair · gemini-2.0-flash

    ul

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ImageContext
    -0.52
     anadolu
    -0.50
     Vla
    -0.49
     simplifié
    -0.48
     Thra
    -0.48
     Edna
    -0.47
     rhiz
    -0.47
    Vla
    -0.46
     erb
    -0.45
     PKK
    -0.45
    POSITIVE LOGITS
    expandindo
    0.86
     So
    0.81
     Sach
    0.77
    SO
    0.76
     SO
    0.74
    so
    0.73
    So
    0.72
    sach
    0.71
     Sul
    0.66
    sona
    0.65
    Activations Density 0.356%

    No Known Activations