© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6301
    Prev
    Next
    INDEX
    Explanations

    words related to cell biology, particularly cell shape and motility

    oai_token-act-pair · gemini-2.0-flash

    cell behavior and morphology

    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
     CreateTagHelper
    -0.90
    ⓧ
    -0.70
    ьа
    -0.63
     transfieras
    -0.62
    تقاوى
    -0.62
     BoxDecoration
    -0.62
     виправивши
    -0.59
    ReusableCell
    -0.59
    UITableViewCell
    -0.59
     تضيفلها
    -0.57
    POSITIVE LOGITS
     contra
    0.61
    zość
    0.52
     ProtoMessage
    0.51
    ILLA
    0.49
     beating
    0.49
    protoc
    0.49
     my
    0.48
    tuo
    0.47
    OrBuilder
    0.47
    ercicio
    0.47
    Activations Density 5.304%

    No Known Activations