© 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. 10945
    Prev
    Next
    INDEX
    Explanations

    sentences describing factors that influence an outcome

    oai_token-act-pair · gemini-2.0-flash

    Discussing factors

    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
     morire
    -0.71
     Baillargeon
    -0.69
    Rhestr
    -0.69
     vectorielles
    -0.67
    NgModule
    -0.66
     vectorielle
    -0.66
     répon
    -0.65
     zelve
    -0.65
     vPvB
    -0.65
     fieldNum
    -0.64
    POSITIVE LOGITS
    delwed
    0.52
    izr
    0.43
     stump
    0.43
     Bi
    0.42
    saraba
    0.41
     account
    0.41
    top
    0.41
     Sept
    0.40
    icap
    0.40
    Especially
    0.40
    Activations Density 2.822%

    No Known Activations