© 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. 13106
    Prev
    Next
    INDEX
    Explanations

    a variety of words, potentially based on context or source, including programming terms, names of places connected to Jewish history, legal terms, and words related to dance.

    oai_token-act-pair · gemini-2.0-flash

    say "of"

    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
     pinulongan
    -0.82
    évaluateur
    -0.71
    getDoctrine
    -0.71
     صوتيه
    -0.69
     nonatomic
    -0.68
     rospy
    -0.67
    DockStyle
    -0.66
     AspNetCore
    -0.66
    WriteBarrier
    -0.66
    Hentet
    -0.65
    POSITIVE LOGITS
     of
    2.41
     của
    0.96
    of
    0.93
     ofthe
    0.90
    ofthe
    0.90
    ของ
    0.86
     Of
    0.83
    OfThe
    0.78
    Of
    0.73
    tof
    0.69
    Activations Density 8.927%

    No Known Activations