© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5946
    Prev
    Next
    INDEX
    Explanations

    words related to Indo-European languages, religion, and medicine, possibly in a list format

    oai_token-act-pair · gemini-2.0-flash

    Code/UI elements

    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
     Pliocene
    -0.45
     PKK
    -0.44
     Poincar
    -0.41
     heretics
    -0.40
     řek
    -0.39
    A
    -0.39
     Diwali
    -0.38
     Whigs
    -0.37
     preachers
    -0.36
     estadual
    -0.36
    POSITIVE LOGITS
    SharedDtor
    0.73
     المعيارى
    0.62
     Theſe
    0.61
    LookAnd
    0.60
     ویکی‌پدیای
    0.57
     NSCoder
    0.56
     Efq
    0.55
     Thời
    0.55
     iconFacebook
    0.55
    KommentareTeilen
    0.54
    Activations Density 15.103%

    No Known Activations