© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5672
    Prev
    Next
    INDEX
    Explanations

    abbreviations for months or geographic locations, and words ending in ings and otion

    oai_token-act-pair · gemini-2.0-flash

    Mo

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Mo
    -2.44
    Mo
    -2.38
     mo
    -2.17
    mo
    -2.09
     MO
    -1.78
    MO
    -1.75
     Mox
    -1.36
     molybdenum
    -1.27
     Мо
    -1.27
    Мо
    -1.25
    POSITIVE LOGITS
     prima
    0.44
     band
    0.44
    Hochspringen
    0.44
    CodedInputStream
    0.42
     Autos
    0.42
     argento
    0.42
    CodeDom
    0.41
    dBm
    0.41
    wend
    0.41
     Band
    0.41
    Activations Density 1.515%

    No Known Activations