© 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. 15844
    Prev
    Next
    INDEX
    Explanations

    clauses or phrases that express a notable or surprising exception or event.

    oai_token-act-pair · gemini-2.0-flash

    "as" in different 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
    Because
    -0.64
     fordi
    -0.62
     Because
    -0.61
    porque
    -0.60
    denn
    -0.60
    Personendaten
    -0.60
     AssemblyCompany
    -0.57
     weil
    -0.56
     porque
    -0.55
     mert
    -0.54
    POSITIVE LOGITS
     as
    2.72
     sebagai
    1.58
    as
    1.27
    作为
    1.24
     как
    1.20
    作為
    1.20
     ως
    1.18
    sebagai
    1.13
     као
    1.13
     Sebagai
    1.10
    Activations Density 2.431%

    No Known Activations