© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13369
    Prev
    Next
    INDEX
    Explanations

    words indicating something occurred at an earlier time

    oai_token-act-pair · gemini-2.0-flash

    previous

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     previous
    -2.77
    previous
    -2.52
    Previous
    -2.38
     Previous
    -2.30
     PREVIOUS
    -1.84
     предыду
    -1.83
     précédente
    -1.55
    PREVIOUS
    -1.55
     précédents
    -1.53
     précédent
    -1.52
    POSITIVE LOGITS
     joaat
    0.69
    wieś
    0.67
    riwal
    0.62
    urally
    0.60
     száz
    0.58
    ValueStyle
    0.57
    TagMode
    0.56
    oweit
    0.55
    брь
    0.54
    Penguin
    0.54
    Activations Density 0.762%

    No Known Activations