© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14260
    Prev
    Next
    INDEX
    Explanations

    statistics from sports games

    oai_token-act-pair · gemini-2.0-flash

    sports statistics

    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
     Савезне
    -0.62
    HomeAsUp
    -0.60
    ForValue
    -0.57
     ExecuteAsync
    -0.56
    ourable
    -0.55
     Италијани
    -0.55
    msgSender
    -0.54
     bezeichneter
    -0.54
    StoreMessageInfo
    -0.53
     AssemblyTitle
    -0.53
    POSITIVE LOGITS
    stridium
    0.48
    zocht
    0.48
    zarchiwizowane
    0.47
     Concert
    0.46
     Logical
    0.46
     Conselho
    0.46
     evaporate
    0.46
     typelib
    0.46
     proton
    0.45
     plong
    0.45
    Activations Density 0.535%

    No Known Activations