© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 245039
    Prev
    Next
    INDEX
    Explanations

    fewer crowds and better prices

    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_40_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
     оптима
    0.43
     optimal
    0.40
    岃
    0.38
    Tourism
    0.37
    🥓
    0.37
     туристи
    0.37
    観光
    0.36
     وتح
    0.36
     ◎
    0.36
    etur
    0.36
    POSITIVE LOGITS
     booking
    0.48
     bookings
    0.45
     cheaper
    0.45
    Booking
    0.44
     visit
    0.43
    booking
    0.43
     Booking
    0.41
    bookings
    0.40
     visiting
    0.39
     reservation
    0.39
    Activations Density 0.010%

    No Known Activations