© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14037
    Prev
    Next
    INDEX
    Explanations

    words from the Croatian language

    oai_token-act-pair · gemini-2.0-flash

    various programming-related terms or line beginnings

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

    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_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
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.71
    djangoproject
    -0.57
    RefNanny
    -0.56
     ProtoMessage
    -0.54
    InvalidProtocol
    -0.53
    ollectionView
    -0.52
     liik
    -0.52
     vergeten
    -0.52
     surla
    -0.50
    $.
    -0.50
    POSITIVE LOGITS
     jScrollPane
    0.52
    Espèce
    0.46
    expects
    0.46
     leb
    0.45
     AspNetCore
    0.44
    exion
    0.44
     مؤرشف
    0.44
    зулта
    0.43
     Uniti
    0.42
     يتيمه
    0.42
    Activations Density 0.860%

    No Known Activations