© 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
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9932
    Prev
    Next
    INDEX
    Explanations

    contexts related to environmental and medical factors and their impacts

    oai_token-act-pair · gemini-2.0-flash

    a

    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
    principalTable
    -0.78
    berdayakan
    -0.77
     fermés
    -0.76
     >=",
    -0.74
     définiti
    -0.73
    uxxxx
    -0.73
    hésite
    -0.73
    findpost
    -0.71
     مرئيه
    -0.71
    featureID
    -0.68
    POSITIVE LOGITS
     transpired
    0.66
     utilised
    0.61
     utilized
    0.61
     utilize
    0.60
     instances
    0.58
     commencing
    0.57
     commenced
    0.56
    ”
    0.56
    als
    0.55
     utilising
    0.55
    Activations Density 1.105%

    No Known Activations