© 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. 9675
    Prev
    Next
    INDEX
    Explanations

    words related to religion, medicine, or scientific studies

    oai_token-act-pair · gemini-2.0-flash

    biological processes

    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
    drawImage
    -0.51
    rov
    -0.44
    gan
    -0.43
    orm
    -0.42
    tagHelper
    -0.41
    tack
    -0.41
    oose
    -0.40
     cold
    -0.39
     cover
    -0.39
    awk
    -0.39
    POSITIVE LOGITS
    CreateModel
    0.75
     NSCoder
    0.69
    tvguidetime
    0.69
     MainAxisSize
    0.69
     ujednoznacz
    0.67
     ProtoMessage
    0.66
    httphttps
    0.66
     propOrder
    0.65
    sizeCache
    0.64
    LabelTagHelper
    0.63
    Activations Density 1.611%

    No Known Activations