© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15618
    Prev
    Next
    INDEX
    Explanations

    conditional statements

    oai_token-act-pair · gemini-2.0-flash

    words signaling subsequent events

    np_token-act-pair-logits · gpt-4o-mini

    "after"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    odeon
    -0.50
    ungguhnya
    -0.48
    tisgarh
    -0.48
    AccessorTable
    -0.47
    detta
    -0.47
    互联网档案馆
    -0.46
    Насе
    -0.46
     GRATU
    -0.45
    openhauer
    -0.45
    ienti
    -0.44
    POSITIVE LOGITS
     after
    3.05
    after
    2.70
     After
    2.45
    After
    2.42
    AFTER
    2.14
     AFTER
    2.13
     dopo
    2.11
     après
    2.03
     setelah
    2.02
     após
    2.02
    Activations Density 4.033%

    No Known Activations