© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12431
    Prev
    Next
    INDEX
    Explanations

    American sports teams or awards.

    oai_token-act-pair · gemini-2.0-flash

    technical terms and references

    np_token-act-pair-logits · gpt-4o-mini

    Oklahoma locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     Wizards
    -0.47
     GILBERT
    -0.45
     verticales
    -0.44
     ervan
    -0.43
     utafitiHapana
    -0.43
    ofe
    -0.43
    มาะ
    -0.43
    rubin
    -0.43
     [+
    -0.42
    Revenge
    -0.42
    POSITIVE LOGITS
     nahilalakip
    0.80
    AccessorTable
    0.69
    RectangleBorder
    0.63
     EconPapers
    0.58
    piecze
    0.58
    ViewFeatures
    0.57
    AnimationsModule
    0.57
    enumi
    0.56
     发表于
    0.56
    MemoryWarning
    0.55
    Activations Density 0.927%

    No Known Activations