© 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. 9896
    Prev
    Next
    INDEX
    Explanations

    a diverse range of words that share a common theme of comparison, balance, and experience

    oai_token-act-pair · gemini-2.0-flash

    a middle state

    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
    ContentAsync
    -0.77
     Efq
    -0.76
     endwhile
    -0.75
    TestingModule
    -0.73
     useAppContext
    -0.70
    NewUrlParser
    -0.69
     onCreateView
    -0.68
     препратки
    -0.67
    kloped
    -0.66
    WriteTagHelper
    -0.65
    POSITIVE LOGITS
     am
    0.91
    bet
    0.75
    Am
    0.74
     Am
    0.73
     bet
    0.67
    Bet
    0.62
    ме
    0.60
    am
    0.60
     Bet
    0.60
     AM
    0.58
    Activations Density 1.073%

    No Known Activations