© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13966
    Prev
    Next
    INDEX
    Explanations

    the German language

    oai_token-act-pair · gemini-2.0-flash

    non-English words

    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
     ſeveral
    -0.52
     laſt
    -0.51
     reaſon
    -0.50
     purpoſe
    -0.50
     ſtate
    -0.49
     ſame
    -0.48
     eccl
    -0.48
     Monfieur
    -0.47
     EconPapers
    -0.47
     preſent
    -0.46
    POSITIVE LOGITS
     Roskov
    0.58
    Хьажоргаш
    0.54
    Билгалдахарш
    0.54
    ibatis
    0.53
     RoutedEventArgs
    0.52
    Personendaten
    0.51
     estimés
    0.51
    Lähteet
    0.51
    WaitGroup
    0.51
    Chham
    0.50
    Activations Density 0.221%

    No Known Activations