© 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. 1140
    Prev
    Next
    INDEX
    Explanations

    travel itinerary, pace, vibe

    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
     Wiggins
    0.40
    $\--
    0.39
     CLUB
    0.39
    ﮑ
    0.39
    劭
    0.38
    ട്ടം
    0.37
    club
    0.37
     Regis
    0.36
    วง
    0.36
    植
    0.36
    POSITIVE LOGITS
    Trip
    0.47
     Trip
    0.46
    Rick
    0.45
     hostel
    0.44
    เที่ยว
    0.44
     Hostel
    0.44
     hostels
    0.44
     touring
    0.42
    Packing
    0.42
    Hiking
    0.41
    Activations Density 0.158%

    No Known Activations