© 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. 13356
    Prev
    Next
    INDEX
    Explanations

    words that are commonly used as prepositions within mathematical writing

    oai_token-act-pair · gemini-2.0-flash

    in

    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
    AsUp
    -0.89
    ItemBackground
    -0.86
     kaynağından
    -0.82
     calendriers
    -0.74
    хьтан
    -0.73
     Numerade
    -0.71
     autorytatywna
    -0.71
     whoſe
    -0.70
     الرياضيه
    -0.70
    رشف
    -0.69
    POSITIVE LOGITS
    getLogger
    0.46
    pakk
    0.46
     como
    0.43
    バリー
    0.43
     feature
    0.42
    ftagPool
    0.42
     го
    0.42
     Whittaker
    0.42
    pronounced
    0.42
     duy
    0.41
    Activations Density 3.910%

    No Known Activations