© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4467
    Prev
    Next
    INDEX
    Explanations

    a combination of seemingly unrelated things including file addresses, network protocols, lab reagents, and code snippets

    oai_token-act-pair · gemini-2.0-flash

    Code and identifiers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    providedIn
    -0.61
     two
    -0.53
     three
    -0.53
    verwijspagina
    -0.53
    떨
    -0.52
     none
    -0.50
    urun
    -0.49
     ed
    -0.47
     duy
    -0.47
    Aiheesta
    -0.47
    POSITIVE LOGITS
     itſelf
    0.91
     stiefel
    0.81
     Geraadpleegd
    0.77
     fevere
    0.76
     Efq
    0.74
     raiſ
    0.73
     myſelf
    0.71
     Reſ
    0.71
     pleaſure
    0.71
     purpoſe
    0.70
    Activations Density 13.296%

    No Known Activations