© 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. 9860
    Prev
    Next
    INDEX
    Explanations

    questions relating to taking an exam or procedure

    oai_token-act-pair · gemini-2.0-flash

    technical snippets

    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
    日閲覧
    -0.52
     roost
    -0.52
    olyb
    -0.51
    enumi
    -0.50
     Roskov
    -0.47
    EndContext
    -0.46
    rungsseite
    -0.45
     \\[
    -0.45
    Pranala
    -0.45
     ویکی‌پدی
    -0.43
    POSITIVE LOGITS
     Efq
    0.66
     crdi
    0.59
    HasAnnotation
    0.59
    CompilerServices
    0.56
    lewati
    0.54
     CWE
    0.54
    ^(@)
    0.53
    Pratique
    0.50
    preduce
    0.50
     xenia
    0.50
    Activations Density 4.363%

    No Known Activations