© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11608
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude

    oai_token-act-pair · gemini-2.0-flash

    Thanks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    thâu
    -0.65
    исленность
    -0.58
     onCancelled
    -0.57
     jadx
    -0.55
     consultato
    -0.54
    setVerticalGroup
    -0.54
    fromCharCode
    -0.52
    WriteLiteral
    -0.52
    newtheorem
    -0.50
    TagMode
    -0.50
    POSITIVE LOGITS
     lot
    0.71
     alot
    0.65
    lots
    0.65
    Lots
    0.57
     Lots
    0.57
    carbons
    0.51
     estimés
    0.51
    alleye
    0.50
     LOT
    0.50
     AppCompat
    0.50
    Activations Density 2.544%

    No Known Activations