© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15844
    Prev
    Next
    INDEX
    Explanations

    Danish words, especially those that may be titles of works

    oai_token-act-pair · gemini-2.0-flash

    foreign language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Inscrivez
    -0.61
    wpi
    -0.60
     Suivez
    -0.60
     Añade
    -0.59
     obiettivo
    -0.58
     han
    -0.56
     reaſon
    -0.54
    modelBuilder
    -0.53
     AppCompatTheme
    -0.53
     has
    -0.53
    POSITIVE LOGITS
     har
    0.75
     disambiguazione
    0.71
    Har
    0.61
     Har
    0.60
     med
    0.56
    har
    0.53
     surla
    0.52
     Med
    0.51
     er
    0.49
    存于互联网档案馆
    0.49
    Activations Density 0.946%

    No Known Activations