© 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. 15871
    Prev
    Next
    INDEX
    Explanations

    numbers with "th" or "nd" after them.

    oai_token-act-pair · gemini-2.0-flash

    say "th"

    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
    WillAppear
    -0.79
    rungsseite
    -0.67
     Efq
    -0.66
    NewUrlParser
    -0.63
     Theſe
    -0.59
    SharedCtor
    -0.59
     للاسماء
    -0.58
     estimés
    -0.57
     Commentaires
    -0.56
    dafx
    -0.55
    POSITIVE LOGITS
    <sup>
    2.64
     ${
    2.13
    ${
    1.77
    <sub>
    1.74
     {@
    1.46
     $^{
    1.43
     {{
    1.36
    {{
    1.34
     "${
    1.34
    /${
    1.30
    Activations Density 1.505%

    No Known Activations