© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12962
    Prev
    Next
    INDEX
    Explanations

    text related to flight simulation

    oai_token-act-pair · gemini-2.0-flash

    Airline industry and flight models

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     flight
    -2.00
     flying
    -1.96
     airplane
    -1.95
     flown
    -1.90
     Flight
    -1.88
     aircraft
    -1.87
     fly
    -1.85
     flights
    -1.82
     flew
    -1.79
     plane
    -1.78
    POSITIVE LOGITS
    umberland
    0.56
    rungsseite
    0.55
     Salinas
    0.53
    addLast
    0.53
    +:+
    0.53
     Norris
    0.51
    TabIndex
    0.50
    wenye
    0.48
     censi
    0.48
     StringTokenizer
    0.48
    Activations Density 0.883%

    No Known Activations