© 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-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10702
    Prev
    Next
    INDEX
    Explanations

    airlines and flight numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_13_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -
    0.55
     carry
    0.52
    ene
    0.52
    .</
    0.50
    ária
    0.47
     assets
    0.47
     techniques
    0.46
     ஒன்ற
    0.46
    .
    0.46
     breakout
    0.46
    POSITIVE LOGITS
    postdata
    0.54
     Où
    0.52
     Airline
    0.52
     Datum
    0.50
    ک
    0.49
     Quelles
    0.49
     Into
    0.48
    ومو
    0.48
    рів
    0.48
    airlines
    0.48
    Activations Density 0.007%

    No Known Activations