© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11908
    Prev
    Next
    INDEX
    Explanations

    a mix of programming code and database queries.

    oai_token-act-pair · gemini-2.0-flash

    code and foreign languages

    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
     useDispatch
    -0.64
    bootstrapcdn
    -0.63
    Ligações
    -0.57
    Viited
    -0.57
    Izvori
    -0.56
    ToUse
    -0.56
     parseFrom
    -0.55
     onCreateView
    -0.55
     Gag
    -0.55
    eqn
    -0.55
    POSITIVE LOGITS
    人民共和国
    0.60
     bēr
    0.53
    ValueStyle
    0.53
     judiciales
    0.52
     gloire
    0.52
     geslacht
    0.52
    richTextPanel
    0.52
     vět
    0.50
     الوطنيه
    0.49
     especiais
    0.48
    Activations Density 1.716%

    No Known Activations