© 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. 6110
    Prev
    Next
    INDEX
    Explanations

    code snippets and figure references

    oai_token-act-pair · gemini-2.0-flash

    code/identifiers

    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
    ="/">
    -0.59
    vägen
    -0.56
    fören
    -0.56
    amemnon
    -0.55
    rådet
    -0.54
     végétale
    -0.54
    jectures
    -0.53
    verket
    -0.52
    duate
    -0.52
    POSED
    -0.51
    POSITIVE LOGITS
     للاسماء
    0.78
    Chham
    0.69
    ValueStyle
    0.68
     ostavi
    0.67
    rungsseite
    0.66
    Hochspringen
    0.63
     onCancelled
    0.62
     rhestr
    0.59
     ExecuteAsync
    0.58
     isInitialized
    0.56
    Activations Density 17.552%

    No Known Activations