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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 3-GEMMASCOPE-TRANSCODER-16K
    4. 8453
    Prev
    Next
    INDEX
    Explanations

    words that relate to whether something is able to be fixed, whether in medicine or otherwise.

    oai_token-act-pair · gemini-2.0-flash

    medical contexts

    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
    SharedDtor
    -0.60
     Sicher
    -0.54
     söyle
    -0.53
    inko
    -0.52
     specchio
    -0.50
     pasteles
    -0.49
     Fleisch
    -0.49
     esternos
    -0.49
     Juin
    -0.47
     skak
    -0.47
    POSITIVE LOGITS
     Treat
    1.64
     treat
    1.63
    treat
    1.62
     TREAT
    1.59
    Treat
    1.55
     treating
    1.53
     Treating
    1.50
     treatment
    1.48
     treats
    1.46
    Treating
    1.46
    Activations Density 0.764%

    No Known Activations