© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2923
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas with many symbols, especially related to frequency

    oai_token-act-pair · gemini-2.0-flash

    i

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     myſelf
    -1.00
     Савезне
    -0.98
     itſelf
    -0.96
     Reſ
    -0.94
     beginnetje
    -0.93
     ་་
    -0.93
     تضيفلها
    -0.92
     raiſ
    -0.90
    EDEFAULT
    -0.90
     iſt
    -0.89
    POSITIVE LOGITS
    ,
    0.48
     session
    0.47
     (
    0.45
     par
    0.45
     må
    0.44
     to
    0.44
     Car
    0.42
     trip
    0.41
     its
    0.41
     im
    0.41
    Activations Density 2.026%

    No Known Activations