© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14025
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols in scientific or legal documents

    oai_token-act-pair · gemini-2.0-flash

    single-digit numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     six
    -1.00
     four
    -0.97
     five
    -0.97
     eight
    -0.92
     seven
    -0.90
     nine
    -0.86
     three
    -0.84
     cinq
    -0.80
     nueve
    -0.79
     oito
    -0.78
    POSITIVE LOGITS
    StoryboardSegue
    0.71
     myſelf
    0.68
     Siamese
    0.68
     localObject
    0.67
     Confucian
    0.66
     Pelop
    0.66
     ―――――
    0.65
     Efq
    0.65
     monasteries
    0.64
     Suez
    0.64
    Activations Density 12.460%

    No Known Activations