© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 218983
    Prev
    Next
    INDEX
    Explanations

    Vietnamese food and culture

    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_31_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
    '),('
    0.40
    ิ่ม
    0.35
    orkel
    0.35
    ⸝
    0.35
    ্রেক
    0.34
     перво
    0.34
    ላ
    0.33
     endpoints
    0.33
    ʙ
    0.33
    ':[
    0.33
    POSITIVE LOGITS
     brilliantly
    0.38
    acketing
    0.38
    दुल
    0.36
     especialista
    0.36
     masterful
    0.35
     специалист
    0.35
     brilliant
    0.35
     certaine
    0.34
     നില
    0.34
     schul
    0.34
    Activations Density 0.001%

    No Known Activations