© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13520
    Prev
    Next
    INDEX
    Explanations

    the word "at" followed by a time

    oai_token-act-pair · gemini-2.0-flash

    at or from

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     везе
    -0.51
     Care
    -0.49
    mtable
    -0.48
     tutti
    -0.47
    protoimpl
    -0.47
    racht
    -0.47
     rendre
    -0.46
     Zeit
    -0.46
    ientôt
    -0.46
    raise
    -0.45
    POSITIVE LOGITS
     وتسجيلات
    0.84
    
    0.73
     afternoon
    0.73
     AssemblyCulture
    0.69
    StackNavigator
    0.67
     MORNING
    0.66
     morning
    0.66
    Morning
    0.65
    RegressionTest
    0.63
     noon
    0.59
    Activations Density 2.423%

    No Known Activations