© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 194959
    Prev
    Next
    INDEX
    Explanations

    airlines (JetBlue, Virgin Blue, Virgin Australia, Air Canada, Level, TAP Air Portugal, Transavia, Norwegian)

    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_15_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
    ger
    0.57
    gel
    0.54
    ion
    0.52
    slan
    0.52
    ters
    0.51
    ral
    0.51
    TrackAngle
    0.50
    ⚕
    0.50
    sl
    0.49
    ToString
    0.48
    POSITIVE LOGITS
     pcMove
    0.56
     spam
    0.50
     выборе
    0.50
     হবেনা
    0.50
    номи
    0.48
     게임
    0.47
     костю
    0.47
     достоин
    0.47
     gameOver
    0.47
    pmm
    0.47
    Activations Density 0.000%

    No Known Activations